Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2475. Min Range: -5.2475
Max Act: 5.2475. Min Act: -0.1700
Data Index: 3382490 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2475. Min Range: -5.2475
Max Act: 5.0600. Min Act: -0.1700
Data Index: 3528591 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2475. Min Range: -5.2475
Max Act: 5.0287. Min Act: -0.1700
Data Index: 7724820 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.9975. Min Act: -0.1700
Data Index: 7252023 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1843775 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.9037. Min Act: -0.1700
Data Index: 1460680 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8725. Min Act: -0.1700
Data Index: 778119 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8725. Min Act: -0.1700
Data Index: 4221205 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8725. Min Act: -0.1700
Data Index: 4677274 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1288828 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8725. Min Act: -0.1700
Data Index: 1528056 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.9037. Min Act: -0.1700
Data Index: 8503345 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8412. Min Act: -0.1700
Data Index: 2005097 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8100. Min Act: -0.1700
Data Index: 2602245 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8412. Min Act: -0.1700
Data Index: 854376 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8412. Min Act: -0.1700
Data Index: 596822 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8100. Min Act: -0.1700
Data Index: 4726135 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8100. Min Act: -0.1700
Data Index: 1109230 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8100. Min Act: -0.1700
Data Index: 3778460 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2475. Min Range: -5.2475
Max Act: 4.8100. Min Act: -0.1700
Data Index: 2309170 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19