Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.5975. Min Act: -0.1700
Data Index: 108590 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.5349. Min Act: -0.1700
Data Index: 3552194 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4879. Min Act: -0.1700
Data Index: 8216073 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4879. Min Act: -0.1700
Data Index: 7972423 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.5036. Min Act: -0.1700
Data Index: 8593367 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4723. Min Act: -0.1700
Data Index: 3202088 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4409. Min Act: -0.1700
Data Index: 4990301 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4409. Min Act: -0.1700
Data Index: 8008676 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4723. Min Act: -0.1700
Data Index: 4710207 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4096. Min Act: -0.1700
Data Index: 4147708 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4096. Min Act: -0.1700
Data Index: 5837202 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.4096. Min Act: -0.1700
Data Index: 4844901 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3939. Min Act: -0.1700
Data Index: 7608937 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3939. Min Act: -0.1700
Data Index: 1856935 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3625. Min Act: -0.1700
Data Index: 4823389 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3939. Min Act: -0.1700
Data Index: 1856933 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3469. Min Act: -0.1700
Data Index: 4609012 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3469. Min Act: -0.1700
Data Index: 676089 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3782. Min Act: -0.1700
Data Index: 3796038 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5975. Min Range: -3.5975
Max Act: 3.3625. Min Act: -0.1700
Data Index: 4293356 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19