Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2057 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.8173. Min Act: -0.1700
Data Index: 3598316 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.6923. Min Act: -0.1700
Data Index: 3932249 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.6298. Min Act: -0.1700
Data Index: 8699837 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.6298. Min Act: -0.1700
Data Index: 1024121 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.4423. Min Act: -0.1700
Data Index: 3913612 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.4423. Min Act: -0.1700
Data Index: 1085751 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.3173. Min Act: -0.1700
Data Index: 696947 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.3798. Min Act: -0.1700
Data Index: 1836995 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.3173. Min Act: -0.1700
Data Index: 211479 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.3798. Min Act: -0.1700
Data Index: 1085750 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.3173. Min Act: -0.1700
Data Index: 3683570 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.2548. Min Act: -0.1700
Data Index: 5269117 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.2548. Min Act: -0.1700
Data Index: 3932248 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1298. Min Act: -0.1700
Data Index: 1031446 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1923. Min Act: -0.1700
Data Index: 3687173 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1923. Min Act: -0.1700
Data Index: 8810415 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1923. Min Act: -0.1700
Data Index: 1085753 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1298. Min Act: -0.1700
Data Index: 3932247 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1298. Min Act: -0.1700
Data Index: 7078848 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8173. Min Range: -9.8173
Max Act: 9.1298. Min Act: -0.1700
Data Index: 3687174 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19