Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.2442. Min Act: -0.1700
Data Index: 7907611 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.2130. Min Act: -0.1700
Data Index: 694646 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.2130. Min Act: -0.1700
Data Index: 8122686 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1817. Min Act: -0.1700
Data Index: 2904862 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1817. Min Act: -0.1700
Data Index: 2993682 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1817. Min Act: -0.1700
Data Index: 2084416 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1192. Min Act: -0.1700
Data Index: 8174083 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1817. Min Act: -0.1700
Data Index: 6858943 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1192. Min Act: -0.1700
Data Index: 4960181 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1192. Min Act: -0.1700
Data Index: 5156356 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2615072 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0567. Min Act: -0.1700
Data Index: 7175366 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0880. Min Act: -0.1700
Data Index: 7266300 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0880. Min Act: -0.1700
Data Index: 6666484 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0880. Min Act: -0.1700
Data Index: 2747215 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0880. Min Act: -0.1700
Data Index: 8789670 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0880. Min Act: -0.1700
Data Index: 5555009 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0567. Min Act: -0.1700
Data Index: 2961023 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0255. Min Act: -0.1700
Data Index: 4084406 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2442. Min Range: -6.2442
Max Act: 6.0255. Min Act: -0.1700
Data Index: 3997431 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19