Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1080. Min Range: -7.1080
Max Act: 7.1080. Min Act: -0.1700
Data Index: 729668 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1080. Min Range: -7.1080
Max Act: 7.0768. Min Act: -0.1700
Data Index: 526270 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.9205. Min Act: -0.1700
Data Index: 439633 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.9518. Min Act: -0.1700
Data Index: 5233657 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.8893. Min Act: -0.1700
Data Index: 8671638 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7643. Min Act: -0.1700
Data Index: 191618 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7643. Min Act: -0.1700
Data Index: 6259833 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7330. Min Act: -0.1700
Data Index: 3581657 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7330. Min Act: -0.1700
Data Index: 5235190 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7018. Min Act: -0.1700
Data Index: 28077 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.7018. Min Act: -0.1700
Data Index: 3138883 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6705. Min Act: -0.1700
Data Index: 254225 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6705. Min Act: -0.1700
Data Index: 1886836 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6393. Min Act: -0.1700
Data Index: 823475 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6393. Min Act: -0.1700
Data Index: 8186 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6393. Min Act: -0.1700
Data Index: 1073253 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6393. Min Act: -0.1700
Data Index: 3751424 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.5768. Min Act: -0.1700
Data Index: 672961 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2665790 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1080. Min Range: -7.1080
Max Act: 6.5768. Min Act: -0.1700
Data Index: 3178340 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19