Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3760 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0843. Min Range: -6.0843
Max Act: 6.0843. Min Act: -0.1700
Data Index: 1330222 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0843. Min Range: -6.0843
Max Act: 6.0218. Min Act: -0.1700
Data Index: 4871218 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 5917119 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9593. Min Act: -0.1700
Data Index: 5742541 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0843. Min Range: -6.0843
Max Act: 6.0218. Min Act: -0.1700
Data Index: 8676216 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 7839572 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9906. Min Act: -0.1700
Data Index: 3069617 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9281. Min Act: -0.1700
Data Index: 2492522 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3660489 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3411175 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.9281. Min Act: -0.1700
Data Index: 4595428 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8968. Min Act: -0.1700
Data Index: 1500737 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8656. Min Act: -0.1700
Data Index: 7293871 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8968. Min Act: -0.1700
Data Index: 597669 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8968. Min Act: -0.1700
Data Index: 6565226 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8968. Min Act: -0.1700
Data Index: 6391428 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8968. Min Act: -0.1700
Data Index: 7443432 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8656. Min Act: -0.1700
Data Index: 217107 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8656. Min Act: -0.1700
Data Index: 5409666 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0843. Min Range: -6.0843
Max Act: 5.8343. Min Act: -0.1700
Data Index: 3697300 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19