Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2137 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.3339. Min Act: -0.1700
Data Index: 7229506 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.3339. Min Act: -0.1700
Data Index: 506679 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.3027. Min Act: -0.1700
Data Index: 8680826 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 3531778 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.3027. Min Act: -0.1700
Data Index: 7010088 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 7524444 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 1911622 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 677835 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 29555 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2714. Min Act: -0.1700
Data Index: 2020139 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2402. Min Act: -0.1700
Data Index: 7045474 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2402. Min Act: -0.1700
Data Index: 638708 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2402. Min Act: -0.1700
Data Index: 4638323 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2089. Min Act: -0.1700
Data Index: 8444903 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.1777. Min Act: -0.1700
Data Index: 477232 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.2089. Min Act: -0.1700
Data Index: 1471296 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.1464. Min Act: -0.1700
Data Index: 3431102 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.1777. Min Act: -0.1700
Data Index: 6321172 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.1777. Min Act: -0.1700
Data Index: 3559496 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3339. Min Range: -4.3339
Max Act: 4.1777. Min Act: -0.1700
Data Index: 2513380 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19