Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3724 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.3226. Min Act: -0.1700
Data Index: 3739084 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.2289. Min Act: -0.1700
Data Index: 1809470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1664. Min Act: -0.1700
Data Index: 8054968 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1351. Min Act: -0.1700
Data Index: 5190621 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1351. Min Act: -0.1700
Data Index: 2026100 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1039. Min Act: -0.1700
Data Index: 5763723 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1351. Min Act: -0.1700
Data Index: 2119195 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.1039. Min Act: -0.1700
Data Index: 545300 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0726. Min Act: -0.1700
Data Index: 2119194 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0726. Min Act: -0.1700
Data Index: 3719485 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0726. Min Act: -0.1700
Data Index: 6097250 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0726. Min Act: -0.1700
Data Index: 8447619 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0101. Min Act: -0.1700
Data Index: 6458906 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 1035994 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 545301 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 123541 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2026101 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 3718628 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 3954674 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3226. Min Range: -5.3226
Max Act: 5.0414. Min Act: -0.1700
Data Index: 3961244 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19