Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.7411. Min Act: -0.1700
Data Index: 3098911 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.6786. Min Act: -0.1700
Data Index: 5367244 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.6786. Min Act: -0.1700
Data Index: 7720995 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.5536. Min Act: -0.1700
Data Index: 440851 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.5536. Min Act: -0.1700
Data Index: 998945 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.4598. Min Act: -0.1700
Data Index: 7194196 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.4286. Min Act: -0.1700
Data Index: 2295776 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.4286. Min Act: -0.1700
Data Index: 6384374 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 1921626 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3973. Min Act: -0.1700
Data Index: 3126290 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 8298650 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 4300745 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3348. Min Act: -0.1700
Data Index: 2254510 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 3658709 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 2769645 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 738140 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3973. Min Act: -0.1700
Data Index: 7017177 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3348. Min Act: -0.1700
Data Index: 3878662 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3348. Min Act: -0.1700
Data Index: 7017178 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7411. Min Range: -4.7411
Max Act: 4.3661. Min Act: -0.1700
Data Index: 6475333 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19