Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3135. Min Range: -7.3135
Max Act: 7.3135. Min Act: -0.1700
Data Index: 6384790 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3135. Min Range: -7.3135
Max Act: 7.1260. Min Act: -0.1700
Data Index: 788403 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.9385. Min Act: -0.1700
Data Index: 4498962 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.6573. Min Act: -0.1700
Data Index: 921926 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.5323. Min Act: -0.1700
Data Index: 1144360 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.5010. Min Act: -0.1700
Data Index: 5137924 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 474173 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4698. Min Act: -0.1700
Data Index: 3710700 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 6194458 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 6107610 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4385. Min Act: -0.1700
Data Index: 6028917 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4073. Min Act: -0.1700
Data Index: 3783575 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4073. Min Act: -0.1700
Data Index: 5794429 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.4073. Min Act: -0.1700
Data Index: 8480624 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 7204605 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3448. Min Act: -0.1700
Data Index: 8267542 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3760. Min Act: -0.1700
Data Index: 553046 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3448. Min Act: -0.1700
Data Index: 5245931 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3448. Min Act: -0.1700
Data Index: 7273630 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3135. Min Range: -7.3135
Max Act: 6.3135. Min Act: -0.1700
Data Index: 553047 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19