Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3585 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3161. Min Range: -8.3161
Max Act: 8.3161. Min Act: -0.1700
Data Index: 2957949 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3161. Min Range: -8.3161
Max Act: 8.2536. Min Act: -0.1700
Data Index: 2621153 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3161. Min Range: -8.3161
Max Act: 8.0036. Min Act: -0.1700
Data Index: 7740785 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.8786. Min Act: -0.1700
Data Index: 3271522 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.8473. Min Act: -0.1700
Data Index: 649044 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.7223. Min Act: -0.1700
Data Index: 4318811 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.6911. Min Act: -0.1700
Data Index: 7695930 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.6911. Min Act: -0.1700
Data Index: 3444991 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.5973. Min Act: -0.1700
Data Index: 7090355 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.6286. Min Act: -0.1700
Data Index: 3130929 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.5661. Min Act: -0.1700
Data Index: 758182 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.5661. Min Act: -0.1700
Data Index: 3096208 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.5348. Min Act: -0.1700
Data Index: 190005 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.4411. Min Act: -0.1700
Data Index: 6476833 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.3786. Min Act: -0.1700
Data Index: 4734095 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.3161. Min Act: -0.1700
Data Index: 6351235 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.2848. Min Act: -0.1700
Data Index: 1567571 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.3161. Min Act: -0.1700
Data Index: 433320 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.2848. Min Act: -0.1700
Data Index: 7690666 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3161. Min Range: -8.3161
Max Act: 7.2848. Min Act: -0.1700
Data Index: 468261 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19