Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 937 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7788. Min Range: -9.7788
Max Act: 9.7788. Min Act: -0.1700
Data Index: 4372815 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7788. Min Range: -9.7788
Max Act: 9.2788. Min Act: -0.1700
Data Index: 816410 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7788. Min Range: -9.7788
Max Act: 9.0913. Min Act: -0.1700
Data Index: 3278980 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.9038. Min Act: -0.1700
Data Index: 3465059 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.8413. Min Act: -0.1700
Data Index: 8268320 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.8413. Min Act: -0.1700
Data Index: 412538 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.7788. Min Act: -0.1700
Data Index: 471739 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.7788. Min Act: -0.1700
Data Index: 504599 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.7788. Min Act: -0.1700
Data Index: 7644895 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.7163. Min Act: -0.1700
Data Index: 3340476 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.7163. Min Act: -0.1700
Data Index: 4836030 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5913. Min Act: -0.1700
Data Index: 6236885 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.6538. Min Act: -0.1700
Data Index: 4997314 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5913. Min Act: -0.1700
Data Index: 6292598 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5913. Min Act: -0.1700
Data Index: 893838 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5288. Min Act: -0.1700
Data Index: 7895954 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5288. Min Act: -0.1700
Data Index: 6342123 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5288. Min Act: -0.1700
Data Index: 485848 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5288. Min Act: -0.1700
Data Index: 6144751 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7788. Min Range: -9.7788
Max Act: 8.5288. Min Act: -0.1700
Data Index: 158557 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19