Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.7849. Min Act: -0.1700
Data Index: 1612557 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.5974. Min Act: -0.1700
Data Index: 6897927 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.6599. Min Act: -0.1700
Data Index: 6242806 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.5349. Min Act: -0.1697
Data Index: 262521 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.4724. Min Act: -0.1700
Data Index: 7369937 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.4099. Min Act: -0.1700
Data Index: 8703043 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.2849. Min Act: -0.1700
Data Index: 4419590 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.2849. Min Act: -0.1700
Data Index: 8508477 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 7136207 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.2224. Min Act: -0.1700
Data Index: 7802325 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.2224. Min Act: -0.1695
Data Index: 319191 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.2224. Min Act: -0.1699
Data Index: 4761477 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.0974. Min Act: -0.1670
Data Index: 5797491 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.0974. Min Act: -0.1691
Data Index: 1102413 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 5878923 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 4463790 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 319822 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 492102 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1695
Data Index: 7877627 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.7849. Min Range: -15.7849
Max Act: 15.1599. Min Act: -0.1700
Data Index: 6880903 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19