Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0598. Min Range: -4.0598
Max Act: 4.0286. Min Act: -0.1700
Data Index: 1638527 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0598. Min Range: -4.0598
Max Act: 4.0598. Min Act: -0.1700
Data Index: 79568 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0598. Min Range: -4.0598
Max Act: 4.0286. Min Act: -0.1700
Data Index: 5726200 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9973. Min Act: -0.1700
Data Index: 1163356 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9973. Min Act: -0.1700
Data Index: 77756 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9661. Min Act: -0.1700
Data Index: 2001472 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9661. Min Act: -0.1700
Data Index: 1914657 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9348. Min Act: -0.1700
Data Index: 232559 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9348. Min Act: -0.1700
Data Index: 1991902 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9348. Min Act: -0.1700
Data Index: 639244 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9035. Min Act: -0.1700
Data Index: 4722691 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9035. Min Act: -0.1700
Data Index: 8468223 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.9035. Min Act: -0.1700
Data Index: 3374343 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8723. Min Act: -0.1700
Data Index: 5872808 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8723. Min Act: -0.1700
Data Index: 251105 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8410. Min Act: -0.1700
Data Index: 418511 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8410. Min Act: -0.1700
Data Index: 2272844 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8410. Min Act: -0.1700
Data Index: 2480052 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8410. Min Act: -0.1700
Data Index: 1593710 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0598. Min Range: -4.0598
Max Act: 3.8410. Min Act: -0.1700
Data Index: 3043061 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19