Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.6287. Min Act: -0.1700
Data Index: 7671610 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.5662. Min Act: -0.1700
Data Index: 2549095 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.5662. Min Act: -0.1700
Data Index: 3855901 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.5349. Min Act: -0.1700
Data Index: 5166825 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4724. Min Act: -0.1700
Data Index: 6436718 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4724. Min Act: -0.1700
Data Index: 5935402 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4412. Min Act: -0.1700
Data Index: 7820639 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4099. Min Act: -0.1700
Data Index: 8697505 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4099. Min Act: -0.1700
Data Index: 7829004 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.4099. Min Act: -0.1700
Data Index: 7247338 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.3787. Min Act: -0.1700
Data Index: 1798870 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.3787. Min Act: -0.1700
Data Index: 8132614 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.3787. Min Act: -0.1700
Data Index: 4762795 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.3162. Min Act: -0.1700
Data Index: 6832772 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.3162. Min Act: -0.1700
Data Index: 6255030 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.2849. Min Act: -0.1700
Data Index: 6058678 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.2849. Min Act: -0.1700
Data Index: 1524421 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.2224. Min Act: -0.1700
Data Index: 3848549 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.2537. Min Act: -0.1700
Data Index: 5689708 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6287. Min Range: -6.6287
Max Act: 6.2537. Min Act: -0.1700
Data Index: 6832771 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19