Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.8289. Min Act: -0.1700
Data Index: 252327 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.5789. Min Act: -0.1700
Data Index: 3134118 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.4539. Min Act: -0.1700
Data Index: 3649903 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.3914. Min Act: -0.1700
Data Index: 5162038 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.3914. Min Act: -0.1700
Data Index: 2226426 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.3289. Min Act: -0.1700
Data Index: 5318039 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2664. Min Act: -0.1700
Data Index: 7270148 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2664. Min Act: -0.1700
Data Index: 5586176 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2664. Min Act: -0.1700
Data Index: 3791494 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2039. Min Act: -0.1700
Data Index: 5284674 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2039. Min Act: -0.1700
Data Index: 4926007 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2039. Min Act: -0.1700
Data Index: 4389875 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2039. Min Act: -0.1700
Data Index: 7206659 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.2039. Min Act: -0.1700
Data Index: 8624221 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.1414. Min Act: -0.1700
Data Index: 8036971 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.0789. Min Act: -0.1700
Data Index: 3487138 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.1414. Min Act: -0.1700
Data Index: 3542706 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.1414. Min Act: -0.1700
Data Index: 2166093 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.1414. Min Act: -0.1700
Data Index: 2013849 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8289. Min Range: -9.8289
Max Act: 9.1414. Min Act: -0.1700
Data Index: 240624 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19