Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2079 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2295. Min Range: -8.2295
Max Act: 8.2295. Min Act: -0.1700
Data Index: 2666406 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2295. Min Range: -8.2295
Max Act: 8.1670. Min Act: -0.1700
Data Index: 3451202 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2295. Min Range: -8.2295
Max Act: 8.0420. Min Act: -0.1700
Data Index: 8724814 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.9170. Min Act: -0.1700
Data Index: 7339795 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.9170. Min Act: -0.1700
Data Index: 3028810 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.7295. Min Act: -0.1700
Data Index: 7616666 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.7920. Min Act: -0.1700
Data Index: 1598485 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.6670. Min Act: -0.1700
Data Index: 5569587 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.6045. Min Act: -0.1700
Data Index: 6279952 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.6045. Min Act: -0.1700
Data Index: 1935359 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.6045. Min Act: -0.1700
Data Index: 8414675 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.6045. Min Act: -0.1700
Data Index: 5108854 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5732. Min Act: -0.1700
Data Index: 3836404 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5732. Min Act: -0.1700
Data Index: 6279953 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5420. Min Act: -0.1700
Data Index: 2547481 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5420. Min Act: -0.1700
Data Index: 4057163 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5420. Min Act: -0.1700
Data Index: 5186890 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5420. Min Act: -0.1700
Data Index: 1344920 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.5107. Min Act: -0.1700
Data Index: 5905202 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2295. Min Range: -8.2295
Max Act: 7.4795. Min Act: -0.1700
Data Index: 8402306 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19