Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 902 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.3296. Min Act: -0.1700
Data Index: 66282 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.2359. Min Act: -0.1700
Data Index: 8512048 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.2046. Min Act: -0.1700
Data Index: 3354092 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.1734. Min Act: -0.1700
Data Index: 7386145 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.1109. Min Act: -0.1700
Data Index: 1577506 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0796. Min Act: -0.1700
Data Index: 4797546 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0171. Min Act: -0.1700
Data Index: 1386630 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3296. Min Range: -5.3296
Max Act: 5.0171. Min Act: -0.1700
Data Index: 7799835 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 5157483 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 2948921 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 7760654 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 4381477 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 2962231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 7407898 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 8827739 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 5888398 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9859. Min Act: -0.1700
Data Index: 8735319 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 8126905 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9234. Min Act: -0.1700
Data Index: 7278087 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3296. Min Range: -5.3296
Max Act: 4.9546. Min Act: -0.1700
Data Index: 2708879 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19