Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 700 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.9994. Min Act: -0.1700
Data Index: 1214430 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.9369. Min Act: -0.1700
Data Index: 384748 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.9057. Min Act: -0.1700
Data Index: 5564371 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.9057. Min Act: -0.1700
Data Index: 3197300 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.9057. Min Act: -0.1700
Data Index: 321661 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8744. Min Act: -0.1700
Data Index: 4268162 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8432. Min Act: -0.1700
Data Index: 5407359 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8432. Min Act: -0.1700
Data Index: 7647698 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8119. Min Act: -0.1700
Data Index: 7342322 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8119. Min Act: -0.1700
Data Index: 1629959 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7807. Min Act: -0.1700
Data Index: 8528944 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.8119. Min Act: -0.1700
Data Index: 1483210 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7807. Min Act: -0.1700
Data Index: 1379670 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7807. Min Act: -0.1700
Data Index: 4722035 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7494. Min Act: -0.1700
Data Index: 627885 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7182. Min Act: -0.1700
Data Index: 3228663 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7494. Min Act: -0.1700
Data Index: 8546498 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7807. Min Act: -0.1700
Data Index: 1690729 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7182. Min Act: -0.1700
Data Index: 3738601 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9994. Min Range: -6.9994
Max Act: 6.7182. Min Act: -0.1700
Data Index: 2487277 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19