Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2512. Min Range: -7.2512
Max Act: 7.2512. Min Act: -0.1700
Data Index: 7705292 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2512. Min Range: -7.2512
Max Act: 7.0950. Min Act: -0.1700
Data Index: 5206969 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.8137. Min Act: -0.1700
Data Index: 3996971 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.6262. Min Act: -0.1700
Data Index: 6995495 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.6262. Min Act: -0.1700
Data Index: 7265715 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.6262. Min Act: -0.1700
Data Index: 3974708 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.5012. Min Act: -0.1700
Data Index: 8607670 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.4700. Min Act: -0.1700
Data Index: 2797612 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.4700. Min Act: -0.1700
Data Index: 8250824 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.4700. Min Act: -0.1700
Data Index: 1311804 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.4075. Min Act: -0.1700
Data Index: 4873572 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 6721775 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.4075. Min Act: -0.1700
Data Index: 884643 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3476317 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 6340596 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 2515479 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 6103247 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 6612236 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.2825. Min Act: -0.1700
Data Index: 6289658 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2512. Min Range: -7.2512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 5021209 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19