Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3962 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.1257. Min Act: -0.1700
Data Index: 2085112 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0945. Min Act: -0.1700
Data Index: 319156 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0945. Min Act: -0.1700
Data Index: 868093 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0945. Min Act: -0.1700
Data Index: 1243425 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0632. Min Act: -0.1700
Data Index: 3934948 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0320. Min Act: -0.1700
Data Index: 5045618 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0007. Min Act: -0.1700
Data Index: 588926 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0007. Min Act: -0.1700
Data Index: 4590846 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0320. Min Act: -0.1700
Data Index: 251259 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1257. Min Range: -4.1257
Max Act: 4.0007. Min Act: -0.1700
Data Index: 4918026 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9695. Min Act: -0.1700
Data Index: 3752249 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9382. Min Act: -0.1700
Data Index: 4048574 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9069. Min Act: -0.1700
Data Index: 2129197 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9069. Min Act: -0.1700
Data Index: 305159 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9069. Min Act: -0.1700
Data Index: 4806615 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9069. Min Act: -0.1700
Data Index: 4465662 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.8757. Min Act: -0.1700
Data Index: 6999769 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.8757. Min Act: -0.1700
Data Index: 7247336 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.9069. Min Act: -0.1700
Data Index: 4891082 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1257. Min Range: -4.1257
Max Act: 3.8131. Min Act: -0.1700
Data Index: 2323818 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19