Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.7041. Min Act: -0.1700
Data Index: 4719336 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.7041. Min Act: -0.1700
Data Index: 1638397 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6416. Min Act: -0.1700
Data Index: 5014600 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6729. Min Act: -0.1700
Data Index: 7329396 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6729. Min Act: -0.1700
Data Index: 194242 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6729. Min Act: -0.1700
Data Index: 8663511 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6729. Min Act: -0.1700
Data Index: 3662399 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6729. Min Act: -0.1700
Data Index: 617610 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6416. Min Act: -0.1700
Data Index: 364708 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6416. Min Act: -0.1700
Data Index: 5930323 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.5791. Min Act: -0.1700
Data Index: 1616796 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 4251160 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 7109996 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 3380856 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 8136573 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 3331050 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 6805366 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.6104. Min Act: -0.1700
Data Index: 7722891 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.5791. Min Act: -0.1700
Data Index: 7109995 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7041. Min Range: -5.7041
Max Act: 5.5791. Min Act: -0.1700
Data Index: 198696 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19