Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2978. Min Range: -6.2978
Max Act: 6.2978. Min Act: -0.1700
Data Index: 7419615 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.8603. Min Act: -0.1700
Data Index: 2010217 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.8603. Min Act: -0.1700
Data Index: 4680278 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.8291. Min Act: -0.1700
Data Index: 961183 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7353. Min Act: -0.1700
Data Index: 1573447 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7353. Min Act: -0.1700
Data Index: 3934365 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7666. Min Act: -0.1700
Data Index: 1464430 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7353. Min Act: -0.1700
Data Index: 7465202 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7353. Min Act: -0.1700
Data Index: 5103078 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7041. Min Act: -0.1700
Data Index: 2159268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7041. Min Act: -0.1700
Data Index: 7701375 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7041. Min Act: -0.1700
Data Index: 1114810 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7041. Min Act: -0.1700
Data Index: 2894616 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6728. Min Act: -0.1700
Data Index: 8258834 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.7041. Min Act: -0.1700
Data Index: 5073676 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6416. Min Act: -0.1700
Data Index: 5812579 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6416. Min Act: -0.1700
Data Index: 7741068 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6103. Min Act: -0.1700
Data Index: 7573983 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6103. Min Act: -0.1700
Data Index: 464550 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2978. Min Range: -6.2978
Max Act: 5.6103. Min Act: -0.1700
Data Index: 4019872 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19