Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5502 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.6129. Min Act: -0.1700
Data Index: 5212470 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.5817. Min Act: -0.1700
Data Index: 3638729 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.4567. Min Act: -0.1700
Data Index: 2067448 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.4567. Min Act: -0.1700
Data Index: 3734198 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.4254. Min Act: -0.1700
Data Index: 7008062 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.3942. Min Act: -0.1700
Data Index: 8739899 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.3317. Min Act: -0.1700
Data Index: 870817 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.3004. Min Act: -0.1700
Data Index: 4223314 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.3004. Min Act: -0.1700
Data Index: 2340720 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.3004. Min Act: -0.1700
Data Index: 6412763 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.2379. Min Act: -0.1700
Data Index: 3397048 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.2379. Min Act: -0.1700
Data Index: 624252 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.2067. Min Act: -0.1700
Data Index: 795754 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.1754. Min Act: -0.1700
Data Index: 1354021 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.2067. Min Act: -0.1700
Data Index: 7985170 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.2379. Min Act: -0.1700
Data Index: 5569279 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4475037 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.1754. Min Act: -0.1700
Data Index: 4352138 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.1754. Min Act: -0.1700
Data Index: 6109701 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6129. Min Range: -5.6129
Max Act: 5.1754. Min Act: -0.1700
Data Index: 7006796 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19