Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7274. Min Range: -9.7274
Max Act: 9.7274. Min Act: -0.1700
Data Index: 3746496 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7274. Min Range: -9.7274
Max Act: 9.1024. Min Act: -0.1700
Data Index: 4705310 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7274. Min Range: -9.7274
Max Act: 9.0399. Min Act: -0.1700
Data Index: 8072441 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7899. Min Act: -0.1700
Data Index: 5378564 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7899. Min Act: -0.1700
Data Index: 1011091 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7899. Min Act: -0.1700
Data Index: 6829281 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7274. Min Act: -0.1700
Data Index: 4413507 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7274. Min Act: -0.1700
Data Index: 4295277 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.6649. Min Act: -0.1700
Data Index: 1856267 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.7274. Min Act: -0.1700
Data Index: 6931700 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.6649. Min Act: -0.1700
Data Index: 2849228 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.6024. Min Act: -0.1700
Data Index: 4913410 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.5399. Min Act: -0.1700
Data Index: 2444483 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.5399. Min Act: -0.1700
Data Index: 8114167 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.5399. Min Act: -0.1700
Data Index: 8795038 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.5399. Min Act: -0.1700
Data Index: 4741150 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.4774. Min Act: -0.1700
Data Index: 3147766 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.4774. Min Act: -0.1700
Data Index: 445642 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.4774. Min Act: -0.1700
Data Index: 6329931 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7274. Min Range: -9.7274
Max Act: 8.3524. Min Act: -0.1700
Data Index: 239806 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19