Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.7590. Min Act: -0.1700
Data Index: 2008797 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.6965. Min Act: -0.1700
Data Index: 675262 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.6652. Min Act: -0.1700
Data Index: 500100 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.4777. Min Act: -0.1700
Data Index: 2572805 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.4777. Min Act: -0.1700
Data Index: 2731594 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.3527. Min Act: -0.1700
Data Index: 7383916 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.3215. Min Act: -0.1700
Data Index: 8309066 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.3215. Min Act: -0.1700
Data Index: 6016953 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2902. Min Act: -0.1700
Data Index: 1412244 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2590. Min Act: -0.1700
Data Index: 7383915 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2590. Min Act: -0.1700
Data Index: 3130701 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2590. Min Act: -0.1700
Data Index: 8429807 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2590. Min Act: -0.1700
Data Index: 818137 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.1965. Min Act: -0.1700
Data Index: 2168080 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2277. Min Act: -0.1700
Data Index: 3314657 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.2277. Min Act: -0.1700
Data Index: 2990253 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.1965. Min Act: -0.1700
Data Index: 7276480 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.1965. Min Act: -0.1700
Data Index: 1512599 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.1965. Min Act: -0.1700
Data Index: 2548492 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7590. Min Range: -6.7590
Max Act: 6.1652. Min Act: -0.1700
Data Index: 8091205 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19