Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1894 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.7164. Min Act: -0.1700
Data Index: 5866610 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.5289. Min Act: -0.1700
Data Index: 5948995 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.4664. Min Act: -0.1700
Data Index: 1099848 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.3414. Min Act: -0.1700
Data Index: 8471765 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.3414. Min Act: -0.1700
Data Index: 8808588 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.2164. Min Act: -0.1700
Data Index: 4245889 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7164. Min Range: -10.7164
Max Act: 10.1539. Min Act: -0.1700
Data Index: 3341902 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.9039. Min Act: -0.1700
Data Index: 5413803 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.9039. Min Act: -0.1700
Data Index: 1328953 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.8414. Min Act: -0.1700
Data Index: 6311828 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.9039. Min Act: -0.1700
Data Index: 4651535 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.8414. Min Act: -0.1700
Data Index: 4098053 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.7789. Min Act: -0.1700
Data Index: 4247160 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.8414. Min Act: -0.1700
Data Index: 4812576 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.7789. Min Act: -0.1700
Data Index: 8189496 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.8414. Min Act: -0.1700
Data Index: 4043409 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.7164. Min Act: -0.1700
Data Index: 318405 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.7789. Min Act: -0.1700
Data Index: 1567448 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.6539. Min Act: -0.1700
Data Index: 1913626 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7164. Min Range: -10.7164
Max Act: 9.5914. Min Act: -0.1700
Data Index: 6550322 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19