Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.3210. Min Act: -0.1700
Data Index: 2790359 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.2585. Min Act: -0.1700
Data Index: 102366 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1335. Min Act: -0.1700
Data Index: 1006534 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.1023. Min Act: -0.1700
Data Index: 6157439 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0398. Min Act: -0.1700
Data Index: 4818803 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0085. Min Act: -0.1700
Data Index: 8115432 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0398. Min Act: -0.1700
Data Index: 7405905 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0085. Min Act: -0.1700
Data Index: 3043283 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0085. Min Act: -0.1700
Data Index: 6808532 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9773. Min Act: -0.1700
Data Index: 2246746 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9773. Min Act: -0.1700
Data Index: 1471197 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9773. Min Act: -0.1700
Data Index: 6404416 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9773. Min Act: -0.1700
Data Index: 1579912 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3210. Min Range: -5.3210
Max Act: 5.0085. Min Act: -0.1700
Data Index: 3234509 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9460. Min Act: -0.1700
Data Index: 1184481 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9460. Min Act: -0.1700
Data Index: 4990634 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9460. Min Act: -0.1700
Data Index: 33364 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9148. Min Act: -0.1700
Data Index: 5051522 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.9148. Min Act: -0.1700
Data Index: 6003756 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3210. Min Range: -5.3210
Max Act: 4.8835. Min Act: -0.1700
Data Index: 6060362 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19