Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3081 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0468. Min Range: -7.0468
Max Act: 7.0156. Min Act: -0.1700
Data Index: 3378110 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0468. Min Range: -7.0468
Max Act: 7.0468. Min Act: -0.1700
Data Index: 3378126 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.8906. Min Act: -0.1700
Data Index: 3377973 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.8593. Min Act: -0.1700
Data Index: 3377964 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.7968. Min Act: -0.1700
Data Index: 6062613 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.7343. Min Act: -0.1700
Data Index: 5158354 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.6718. Min Act: -0.1700
Data Index: 1700904 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.6406. Min Act: -0.1700
Data Index: 4222304 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.6093. Min Act: -0.1700
Data Index: 3386820 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4503565 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.5468. Min Act: -0.1700
Data Index: 6062275 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4843. Min Act: -0.1700
Data Index: 8560261 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.5156. Min Act: -0.1700
Data Index: 4494393 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4531. Min Act: -0.1700
Data Index: 4435330 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4843. Min Act: -0.1700
Data Index: 167131 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4843. Min Act: -0.1700
Data Index: 3094839 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4531. Min Act: -0.1700
Data Index: 676936 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4531. Min Act: -0.1700
Data Index: 4285446 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4218. Min Act: -0.1700
Data Index: 6999946 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0468. Min Range: -7.0468
Max Act: 6.4218. Min Act: -0.1700
Data Index: 7296150 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19