Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.5117. Min Act: -0.1700
Data Index: 3648743 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.4180. Min Act: -0.1700
Data Index: 919402 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2930. Min Act: -0.1700
Data Index: 8262995 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2617. Min Act: -0.1700
Data Index: 8266812 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2617. Min Act: -0.1700
Data Index: 2144927 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2617. Min Act: -0.1700
Data Index: 1127892 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2305. Min Act: -0.1700
Data Index: 1463358 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2617. Min Act: -0.1700
Data Index: 2371415 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.2305. Min Act: -0.1700
Data Index: 2135802 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1992. Min Act: -0.1700
Data Index: 46942 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1992. Min Act: -0.1700
Data Index: 2093531 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1992. Min Act: -0.1700
Data Index: 655127 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1992. Min Act: -0.1700
Data Index: 7482901 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1680. Min Act: -0.1700
Data Index: 2497856 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1680. Min Act: -0.1700
Data Index: 595207 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1680. Min Act: -0.1700
Data Index: 3602492 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1367. Min Act: -0.1700
Data Index: 3148038 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1055. Min Act: -0.1700
Data Index: 1742344 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.1055. Min Act: -0.1700
Data Index: 2905732 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5117. Min Range: -7.5117
Max Act: 7.0742. Min Act: -0.1700
Data Index: 4892664 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19