Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.6016. Min Act: -0.1700
Data Index: 6110776 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.6016. Min Act: -0.1700
Data Index: 7120483 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.5546. Min Act: -0.1700
Data Index: 7201446 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.5233. Min Act: -0.1700
Data Index: 862527 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.4920. Min Act: -0.1700
Data Index: 4903587 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.4763. Min Act: -0.1700
Data Index: 7590756 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3666. Min Act: -0.1700
Data Index: 5779077 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3666. Min Act: -0.1700
Data Index: 3011072 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3666. Min Act: -0.1700
Data Index: 6432186 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3666. Min Act: -0.1700
Data Index: 2618074 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3195. Min Act: -0.1700
Data Index: 2327858 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3195. Min Act: -0.1700
Data Index: 5709503 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3195. Min Act: -0.1700
Data Index: 4713673 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3038. Min Act: -0.1700
Data Index: 7043859 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3038. Min Act: -0.1700
Data Index: 8829216 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.2881. Min Act: -0.1700
Data Index: 1482471 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.2881. Min Act: -0.1700
Data Index: 624079 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.2881. Min Act: -0.1700
Data Index: 6019238 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.3038. Min Act: -0.1700
Data Index: 7393530 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6016. Min Range: -3.6016
Max Act: 3.2881. Min Act: -0.1700
Data Index: 1262066 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19