Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4677 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.7216. Min Act: -0.1700
Data Index: 7322242 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.2840. Min Act: -0.1700
Data Index: 3840827 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.2215. Min Act: -0.1700
Data Index: 4202904 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1903. Min Act: -0.1700
Data Index: 834167 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 1939334 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 7493958 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 1677948 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 834667 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 7318625 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0965. Min Act: -0.1700
Data Index: 7642840 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 1513567 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 7159406 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.1278. Min Act: -0.1700
Data Index: 2077701 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0965. Min Act: -0.1700
Data Index: 7318636 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 2901539 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 6369615 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 5928017 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 5914721 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 1716425 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7216. Min Range: -4.7216
Max Act: 4.0653. Min Act: -0.1700
Data Index: 768461 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19