Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.5483. Min Act: -0.1700
Data Index: 8487659 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.5483. Min Act: -0.1700
Data Index: 945156 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.1733. Min Act: -0.1700
Data Index: 4265620 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.1108. Min Act: -0.1700
Data Index: 6898231 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.1733. Min Act: -0.1700
Data Index: 3593837 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.1108. Min Act: -0.1700
Data Index: 8806624 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.1108. Min Act: -0.1700
Data Index: 6314725 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5483. Min Range: -9.5483
Max Act: 9.0483. Min Act: -0.1700
Data Index: 96417 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9858. Min Act: -0.1700
Data Index: 8748244 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9858. Min Act: -0.1700
Data Index: 4220046 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9858. Min Act: -0.1700
Data Index: 1568715 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9233. Min Act: -0.1700
Data Index: 8244166 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9858. Min Act: -0.1700
Data Index: 3967981 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.9233. Min Act: -0.1700
Data Index: 2279694 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.8608. Min Act: -0.1700
Data Index: 1498615 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.8608. Min Act: -0.1700
Data Index: 4350740 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.7983. Min Act: -0.1700
Data Index: 7862181 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.7983. Min Act: -0.1700
Data Index: 7611402 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.7983. Min Act: -0.1700
Data Index: 3769461 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5483. Min Range: -9.5483
Max Act: 8.7358. Min Act: -0.1700
Data Index: 682615 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19