Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.4278. Min Act: -0.1700
Data Index: 7808243 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.4278. Min Act: -0.1700
Data Index: 2455918 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.3341. Min Act: -0.1700
Data Index: 4312758 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.2716. Min Act: -0.1700
Data Index: 3010900 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.3028. Min Act: -0.1700
Data Index: 3394952 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4223579 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.3028. Min Act: -0.1700
Data Index: 867729 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.3028. Min Act: -0.1700
Data Index: 4899481 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.2716. Min Act: -0.1700
Data Index: 4308209 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.2403. Min Act: -0.1700
Data Index: 1980521 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1778. Min Act: -0.1700
Data Index: 4801483 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1778. Min Act: -0.1700
Data Index: 6277660 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1778. Min Act: -0.1700
Data Index: 2476311 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1466. Min Act: -0.1700
Data Index: 2975294 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1466. Min Act: -0.1700
Data Index: 4942326 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1153. Min Act: -0.1700
Data Index: 5157619 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1466. Min Act: -0.1700
Data Index: 1836962 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1153. Min Act: -0.1700
Data Index: 4367912 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1153. Min Act: -0.1700
Data Index: 6389586 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4278. Min Range: -5.4278
Max Act: 5.1153. Min Act: -0.1700
Data Index: 3366101 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19