Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.9310. Min Act: -0.1700
Data Index: 3965404 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.8373. Min Act: -0.1700
Data Index: 4927915 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.8373. Min Act: -0.1700
Data Index: 2788833 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.8060. Min Act: -0.1700
Data Index: 2967358 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.7435. Min Act: -0.1700
Data Index: 3127566 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.7435. Min Act: -0.1700
Data Index: 3067383 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.6810. Min Act: -0.1700
Data Index: 1769888 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.7123. Min Act: -0.1700
Data Index: 5276305 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.6810. Min Act: -0.1700
Data Index: 4999539 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.6185. Min Act: -0.1700
Data Index: 605334 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3306036 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 6201514 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 3245815 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5873. Min Act: -0.1700
Data Index: 7676920 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 7808072 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5248. Min Act: -0.1700
Data Index: 1809401 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5248. Min Act: -0.1700
Data Index: 6860302 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 7079086 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 3965403 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9310. Min Range: -5.9310
Max Act: 5.5560. Min Act: -0.1700
Data Index: 2801363 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19