Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5261 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3182. Min Range: -12.3182
Max Act: 12.3182. Min Act: -0.1700
Data Index: 7416020 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3182. Min Range: -12.3182
Max Act: 12.0057. Min Act: -0.1700
Data Index: 4769215 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.6932. Min Act: -0.1700
Data Index: 7078539 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.3807. Min Act: -0.1700
Data Index: 589180 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.3807. Min Act: -0.1700
Data Index: 1115241 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.2557. Min Act: -0.1700
Data Index: 5487281 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.2557. Min Act: -0.1700
Data Index: 1389316 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.2557. Min Act: -0.1700
Data Index: 1895839 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.1932. Min Act: -0.1700
Data Index: 1124844 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.1932. Min Act: -0.1700
Data Index: 97535 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.1932. Min Act: -0.1700
Data Index: 4874986 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.1307. Min Act: -0.1700
Data Index: 5580402 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.1307. Min Act: -0.1700
Data Index: 5115599 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.0682. Min Act: -0.1700
Data Index: 8377118 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3182. Min Range: -12.3182
Max Act: 11.0682. Min Act: -0.1700
Data Index: 5668936 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3182. Min Range: -12.3182
Max Act: 10.9432. Min Act: -0.1700
Data Index: 2737489 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3182. Min Range: -12.3182
Max Act: 10.9432. Min Act: -0.1700
Data Index: 2640947 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3182. Min Range: -12.3182
Max Act: 10.9432. Min Act: -0.1700
Data Index: 160949 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3182. Min Range: -12.3182
Max Act: 10.9432. Min Act: -0.1700
Data Index: 871164 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3182. Min Range: -12.3182
Max Act: 10.9432. Min Act: -0.1700
Data Index: 3269827 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19