Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.9307. Min Act: -0.1700
Data Index: 7831987 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7718. Min Act: -0.1700
Data Index: 6553119 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 8249562 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 6539328 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7239. Min Act: -0.1700
Data Index: 5306232 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6919. Min Act: -0.1700
Data Index: 3843227 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7239. Min Act: -0.1700
Data Index: 6749391 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7239. Min Act: -0.1700
Data Index: 6578506 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6919. Min Act: -0.1700
Data Index: 8242176 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6599. Min Act: -0.1700
Data Index: 5059815 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6759. Min Act: -0.1700
Data Index: 7344701 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6599. Min Act: -0.1700
Data Index: 2891228 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6278. Min Act: -0.1700
Data Index: 7812454 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6117. Min Act: -0.1700
Data Index: 6785920 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.5956. Min Act: -0.1700
Data Index: 7564969 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6117. Min Act: -0.1700
Data Index: 1726038 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.6278. Min Act: -0.1700
Data Index: 8595679 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.5956. Min Act: -0.1700
Data Index: 35671 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.5956. Min Act: -0.1700
Data Index: 4096338 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.5956. Min Act: -0.1700
Data Index: 3487782 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19