Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1263 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1778. Min Range: -8.1778
Max Act: 8.1778. Min Act: -0.1700
Data Index: 3136409 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1778. Min Range: -8.1778
Max Act: 8.0528. Min Act: -0.1700
Data Index: 7683911 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.9903. Min Act: -0.1700
Data Index: 5443041 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.8966. Min Act: -0.1700
Data Index: 395711 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.8028. Min Act: -0.1700
Data Index: 6601239 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.7403. Min Act: -0.1700
Data Index: 2990570 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.7403. Min Act: -0.1700
Data Index: 8313677 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.7091. Min Act: -0.1700
Data Index: 1429478 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.5841. Min Act: -0.1700
Data Index: 2448685 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.6153. Min Act: -0.1700
Data Index: 4445481 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.5841. Min Act: -0.1700
Data Index: 176347 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.4903. Min Act: -0.1700
Data Index: 4984321 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.4903. Min Act: -0.1700
Data Index: 8425153 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.4278. Min Act: -0.1700
Data Index: 6671721 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.4278. Min Act: -0.1700
Data Index: 1224511 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.5216. Min Act: -0.1700
Data Index: 4537040 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.3966. Min Act: -0.1700
Data Index: 6635713 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.3653. Min Act: -0.1700
Data Index: 3441216 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.3653. Min Act: -0.1700
Data Index: 7606594 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1778. Min Range: -8.1778
Max Act: 7.3653. Min Act: -0.1700
Data Index: 634439 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19