Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2312. Min Range: -7.2312
Max Act: 7.2312. Min Act: -0.1700
Data Index: 2971126 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.9500. Min Act: -0.1700
Data Index: 1289805 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.9500. Min Act: -0.1700
Data Index: 271837 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.9187. Min Act: -0.1700
Data Index: 2210395 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.8250. Min Act: -0.1700
Data Index: 4662659 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.8250. Min Act: -0.1700
Data Index: 686785 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.7625. Min Act: -0.1700
Data Index: 7420100 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.7312. Min Act: -0.1700
Data Index: 3221281 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6687. Min Act: -0.1700
Data Index: 7104429 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6687. Min Act: -0.1700
Data Index: 174610 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6375. Min Act: -0.1700
Data Index: 5214212 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 424095 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 1095831 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 4789431 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 6078692 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.6062. Min Act: -0.1700
Data Index: 3161278 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.5750. Min Act: -0.1700
Data Index: 752747 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.5750. Min Act: -0.1700
Data Index: 5894956 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.5437. Min Act: -0.1700
Data Index: 2053731 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2312. Min Range: -7.2312
Max Act: 6.5437. Min Act: -0.1700
Data Index: 2207322 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19