Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3251. Min Range: -7.3251
Max Act: 7.3251. Min Act: -0.1700
Data Index: 5741537 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.9188. Min Act: -0.1700
Data Index: 4522839 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.8251. Min Act: -0.1700
Data Index: 1766456 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.8251. Min Act: -0.1700
Data Index: 101312 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.7938. Min Act: -0.1700
Data Index: 5052412 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.7938. Min Act: -0.1700
Data Index: 5938954 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.7626. Min Act: -0.1700
Data Index: 6048559 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.7313. Min Act: -0.1700
Data Index: 5990608 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.7001. Min Act: -0.1700
Data Index: 5251221 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 4293354 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 7950997 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 7461432 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 1656179 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 5662522 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6376. Min Act: -0.1700
Data Index: 6455581 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6063. Min Act: -0.1700
Data Index: 14260 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6063. Min Act: -0.1700
Data Index: 4219835 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.6063. Min Act: -0.1700
Data Index: 1710832 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.5751. Min Act: -0.1700
Data Index: 2591900 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3251. Min Range: -7.3251
Max Act: 6.5751. Min Act: -0.1700
Data Index: 7614434 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19