Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.8066. Min Act: -0.1700
Data Index: 2459158 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4629. Min Act: -0.1700
Data Index: 4040814 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4316. Min Act: -0.1700
Data Index: 3073420 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4316. Min Act: -0.1700
Data Index: 1251000 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4316. Min Act: -0.1700
Data Index: 2922614 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3691. Min Act: -0.1700
Data Index: 6594628 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4004. Min Act: -0.1700
Data Index: 7195389 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4004. Min Act: -0.1700
Data Index: 7387347 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4004. Min Act: -0.1700
Data Index: 5185147 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.4004. Min Act: -0.1700
Data Index: 3182816 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3691. Min Act: -0.1700
Data Index: 4157108 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3691. Min Act: -0.1700
Data Index: 2020554 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3379. Min Act: -0.1700
Data Index: 6382096 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3379. Min Act: -0.1700
Data Index: 752502 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3379. Min Act: -0.1700
Data Index: 3855918 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3379. Min Act: -0.1700
Data Index: 1858488 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3066. Min Act: -0.1700
Data Index: 5295384 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.3066. Min Act: -0.1700
Data Index: 6599115 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.2754. Min Act: -0.1700
Data Index: 5670931 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8066. Min Range: -5.8066
Max Act: 5.2754. Min Act: -0.1700
Data Index: 5914443 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19