Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.4296. Min Act: -0.1700
Data Index: 940878 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3983. Min Act: -0.1700
Data Index: 8744159 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3983. Min Act: -0.1700
Data Index: 4653346 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3358. Min Act: -0.1700
Data Index: 5977810 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3046. Min Act: -0.1700
Data Index: 2160394 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3046. Min Act: -0.1700
Data Index: 6029668 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.3046. Min Act: -0.1700
Data Index: 1853943 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.2733. Min Act: -0.1700
Data Index: 4839361 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.2733. Min Act: -0.1700
Data Index: 3868948 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.2421. Min Act: -0.1700
Data Index: 8231321 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.2108. Min Act: -0.1700
Data Index: 107149 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.1796. Min Act: -0.1700
Data Index: 944863 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.1796. Min Act: -0.1700
Data Index: 3131998 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.1483. Min Act: -0.1700
Data Index: 1119438 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.0858. Min Act: -0.1700
Data Index: 7201231 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.0546. Min Act: -0.1700
Data Index: 8823503 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4296. Min Range: -6.4296
Max Act: 6.0546. Min Act: -0.1700
Data Index: 7830399 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4296. Min Range: -6.4296
Max Act: 5.9608. Min Act: -0.1700
Data Index: 7824268 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4296. Min Range: -6.4296
Max Act: 5.9296. Min Act: -0.1700
Data Index: 3826376 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4296. Min Range: -6.4296
Max Act: 5.9296. Min Act: -0.1700
Data Index: 667560 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19