Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 608 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.6502. Min Act: -0.1700
Data Index: 3873368 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.5565. Min Act: -0.1700
Data Index: 2454701 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.4627. Min Act: -0.1700
Data Index: 3781987 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.4627. Min Act: -0.1700
Data Index: 4887597 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.4315. Min Act: -0.1700
Data Index: 1832716 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.4315. Min Act: -0.1700
Data Index: 7615869 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.4002. Min Act: -0.1700
Data Index: 2197912 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.3065. Min Act: -0.1700
Data Index: 824070 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2752. Min Act: -0.1700
Data Index: 8728542 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.3065. Min Act: -0.1700
Data Index: 2024897 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2752. Min Act: -0.1700
Data Index: 6441272 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2752. Min Act: -0.1700
Data Index: 7635570 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2752. Min Act: -0.1700
Data Index: 4204218 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2440. Min Act: -0.1700
Data Index: 309574 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2440. Min Act: -0.1700
Data Index: 6728786 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2440. Min Act: -0.1700
Data Index: 2372512 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2440. Min Act: -0.1700
Data Index: 890706 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2440. Min Act: -0.1700
Data Index: 1126355 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2127. Min Act: -0.1700
Data Index: 5534766 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6502. Min Range: -4.6502
Max Act: 4.2127. Min Act: -0.1700
Data Index: 1451016 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19