Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3503. Min Range: -9.3503
Max Act: 9.3503. Min Act: -0.1700
Data Index: 5934322 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3503. Min Range: -9.3503
Max Act: 9.1003. Min Act: -0.1700
Data Index: 8135945 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.5378. Min Act: -0.1700
Data Index: 4089695 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.3503. Min Act: -0.1700
Data Index: 2017208 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.2253. Min Act: -0.1700
Data Index: 7555314 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.1003. Min Act: -0.1700
Data Index: 4154771 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.1003. Min Act: -0.1700
Data Index: 2231319 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.1003. Min Act: -0.1700
Data Index: 2171085 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.0378. Min Act: -0.1700
Data Index: 4714594 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3503. Min Range: -9.3503
Max Act: 8.1003. Min Act: -0.1700
Data Index: 3915212 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.9753. Min Act: -0.1700
Data Index: 2131975 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.9753. Min Act: -0.1700
Data Index: 3216280 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.9753. Min Act: -0.1700
Data Index: 2363078 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.9128. Min Act: -0.1700
Data Index: 5789974 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 7237897 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4747552 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4960738 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 861541 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 4648161 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3503. Min Range: -9.3503
Max Act: 7.8503. Min Act: -0.1700
Data Index: 1375537 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19