Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.7750. Min Act: -0.1700
Data Index: 6650556 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.7437. Min Act: -0.1700
Data Index: 7257777 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.6812. Min Act: -0.1700
Data Index: 4199300 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.6500. Min Act: -0.1699
Data Index: 7675849 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.6500. Min Act: -0.1700
Data Index: 7584030 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5875. Min Act: -0.1700
Data Index: 4232662 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5875. Min Act: -0.1699
Data Index: 2964368 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5562. Min Act: -0.1700
Data Index: 7380318 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5250. Min Act: -0.1700
Data Index: 7674705 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5250. Min Act: -0.1700
Data Index: 968237 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5250. Min Act: -0.1700
Data Index: 2225135 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5250. Min Act: -0.1700
Data Index: 5519883 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.5250. Min Act: -0.1700
Data Index: 1631777 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4937. Min Act: -0.1700
Data Index: 521296 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4625. Min Act: -0.1698
Data Index: 8443462 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4937. Min Act: -0.1700
Data Index: 4557927 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4937. Min Act: -0.1700
Data Index: 2468295 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4937. Min Act: -0.1700
Data Index: 4564799 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4625. Min Act: -0.1700
Data Index: 2226338 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7750. Min Range: -5.7750
Max Act: 5.4625. Min Act: -0.1700
Data Index: 3002472 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19