Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1371 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0401. Min Range: -4.0401
Max Act: 4.0401. Min Act: -0.1700
Data Index: 1167967 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0401. Min Range: -4.0401
Max Act: 4.0089. Min Act: -0.1700
Data Index: 4488856 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0401. Min Range: -4.0401
Max Act: 4.0401. Min Act: -0.1700
Data Index: 3496640 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.8526. Min Act: -0.1700
Data Index: 2905613 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.8682. Min Act: -0.1700
Data Index: 5241363 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.8682. Min Act: -0.1700
Data Index: 5468967 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.8057. Min Act: -0.1700
Data Index: 8811807 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7587. Min Act: -0.1700
Data Index: 2074093 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7431. Min Act: -0.1700
Data Index: 4838673 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7275. Min Act: -0.1700
Data Index: 927679 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7431. Min Act: -0.1700
Data Index: 3835067 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7275. Min Act: -0.1700
Data Index: 3013956 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.7275. Min Act: -0.1700
Data Index: 2340810 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6649. Min Act: -0.1700
Data Index: 4789330 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6962. Min Act: -0.1700
Data Index: 6946275 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6649. Min Act: -0.1700
Data Index: 3837724 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6805. Min Act: -0.1700
Data Index: 787424 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6649. Min Act: -0.1700
Data Index: 8074596 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6805. Min Act: -0.1700
Data Index: 3782477 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0401. Min Range: -4.0401
Max Act: 3.6805. Min Act: -0.1700
Data Index: 2524384 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19