Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0251. Min Range: -6.0251
Max Act: 6.0251. Min Act: -0.1700
Data Index: 8062503 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.9939. Min Act: -0.1700
Data Index: 7576358 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.9314. Min Act: -0.1700
Data Index: 2878368 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.9314. Min Act: -0.1700
Data Index: 750178 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.9001. Min Act: -0.1700
Data Index: 7576360 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.9314. Min Act: -0.1700
Data Index: 429499 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8689. Min Act: -0.1700
Data Index: 2799193 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8689. Min Act: -0.1700
Data Index: 7576362 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8376. Min Act: -0.1700
Data Index: 429500 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8376. Min Act: -0.1700
Data Index: 429497 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8376. Min Act: -0.1700
Data Index: 2799182 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8689. Min Act: -0.1700
Data Index: 7576359 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8376. Min Act: -0.1700
Data Index: 7220775 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.7751. Min Act: -0.1700
Data Index: 1004292 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8064. Min Act: -0.1700
Data Index: 4388961 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8064. Min Act: -0.1700
Data Index: 7576361 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2878366 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.7751. Min Act: -0.1699
Data Index: 3957225 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.7751. Min Act: -0.1700
Data Index: 2878369 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0251. Min Range: -6.0251
Max Act: 5.7439. Min Act: -0.1700
Data Index: 2878365 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19