Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1457 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.4966. Min Act: -0.1700
Data Index: 8080601 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.3091. Min Act: -0.1700
Data Index: 6598519 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.2778. Min Act: -0.1700
Data Index: 7388639 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.2153. Min Act: -0.1700
Data Index: 6225012 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.1841. Min Act: -0.1700
Data Index: 5188905 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.2466. Min Act: -0.1700
Data Index: 2856744 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.0903. Min Act: -0.1700
Data Index: 7658756 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.1216. Min Act: -0.1700
Data Index: 1241899 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.1216. Min Act: -0.1700
Data Index: 8159305 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.0903. Min Act: -0.1700
Data Index: 4945651 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.0278. Min Act: -0.1700
Data Index: 7582977 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4966. Min Range: -7.4966
Max Act: 7.0278. Min Act: -0.1700
Data Index: 6494389 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.9653. Min Act: -0.1700
Data Index: 7284284 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.9341. Min Act: -0.1700
Data Index: 5897981 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.9028. Min Act: -0.1700
Data Index: 8726643 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.8716. Min Act: -0.1700
Data Index: 7178325 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.8716. Min Act: -0.1700
Data Index: 7249811 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.8716. Min Act: -0.1700
Data Index: 5622520 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.8403. Min Act: -0.1700
Data Index: 3331171 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4966. Min Range: -7.4966
Max Act: 6.8403. Min Act: -0.1700
Data Index: 6002454 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19