Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.9852. Min Act: -0.1700
Data Index: 7317212 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.9852. Min Act: -0.1700
Data Index: 8335511 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0164. Min Range: -7.0164
Max Act: 7.0164. Min Act: -0.1700
Data Index: 2872505 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.9227. Min Act: -0.1700
Data Index: 5536720 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.8289. Min Act: -0.1700
Data Index: 981295 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.8289. Min Act: -0.1700
Data Index: 7078751 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.8289. Min Act: -0.1700
Data Index: 460608 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7977. Min Act: -0.1700
Data Index: 5150800 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7977. Min Act: -0.1700
Data Index: 2406568 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7977. Min Act: -0.1700
Data Index: 5355870 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 2859199 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7647305 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 66165 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7578115 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7209913 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 7038340 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7664. Min Act: -0.1700
Data Index: 8458706 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7352. Min Act: -0.1700
Data Index: 6104159 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7352. Min Act: -0.1700
Data Index: 45241 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0164. Min Range: -7.0164
Max Act: 6.7352. Min Act: -0.1700
Data Index: 858971 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19