Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6663. Min Act: -0.1700
Data Index: 4232114 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6351. Min Act: -0.1700
Data Index: 8728002 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6351. Min Act: -0.1700
Data Index: 192896 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6351. Min Act: -0.1700
Data Index: 3462493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6663. Min Act: -0.1700
Data Index: 6094809 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6038. Min Act: -0.1700
Data Index: 8710040 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.6038. Min Act: -0.1700
Data Index: 3070278 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.5101. Min Act: -0.1700
Data Index: 5637237 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.5413. Min Act: -0.1700
Data Index: 2650832 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.5101. Min Act: -0.1700
Data Index: 4717787 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.4788. Min Act: -0.1700
Data Index: 2255138 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.4788. Min Act: -0.1700
Data Index: 7744732 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.4163. Min Act: -0.1700
Data Index: 4624262 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.4476. Min Act: -0.1700
Data Index: 8675714 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.4163. Min Act: -0.1700
Data Index: 8721721 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.3538. Min Act: -0.1700
Data Index: 131755 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.3851. Min Act: -0.1700
Data Index: 2997797 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.3851. Min Act: -0.1700
Data Index: 4396120 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.3538. Min Act: -0.1700
Data Index: 117324 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6663. Min Range: -7.6663
Max Act: 7.3538. Min Act: -0.1700
Data Index: 6353440 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19