Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1253 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.6510. Min Act: -0.1700
Data Index: 6364751 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.3385. Min Act: -0.1700
Data Index: 2573575 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.3072. Min Act: -0.1700
Data Index: 1693595 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.2447. Min Act: -0.1700
Data Index: 4097133 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.2760. Min Act: -0.1700
Data Index: 2371077 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.2135. Min Act: -0.1700
Data Index: 6883151 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.2135. Min Act: -0.1700
Data Index: 8272065 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.1822. Min Act: -0.1700
Data Index: 8250445 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.1822. Min Act: -0.1700
Data Index: 2672466 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.1822. Min Act: -0.1700
Data Index: 7773769 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.1510. Min Act: -0.1700
Data Index: 1475035 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.1197. Min Act: -0.1700
Data Index: 1807599 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0885. Min Act: -0.1700
Data Index: 7367535 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 5506663 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 1237423 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 3105986 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0260. Min Act: -0.1700
Data Index: 1183053 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0260. Min Act: -0.1700
Data Index: 8295738 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6510. Min Range: -6.6510
Max Act: 6.0260. Min Act: -0.1700
Data Index: 6964320 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6510. Min Range: -6.6510
Max Act: 5.9947. Min Act: -0.1700
Data Index: 3412722 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19