Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5125 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.8867. Min Act: -0.1700
Data Index: 3558639 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.8242. Min Act: -0.1700
Data Index: 2280533 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.7617. Min Act: -0.1700
Data Index: 7466804 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.6367. Min Act: -0.1700
Data Index: 3667052 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.5742. Min Act: -0.1700
Data Index: 4656082 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.5117. Min Act: -0.1700
Data Index: 1108904 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.4492. Min Act: -0.1700
Data Index: 3391868 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.3867. Min Act: -0.1700
Data Index: 3502082 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.3867. Min Act: -0.1700
Data Index: 1599974 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.3242. Min Act: -0.1700
Data Index: 4840345 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1992. Min Act: -0.1700
Data Index: 1396790 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1992. Min Act: -0.1700
Data Index: 61062 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1992. Min Act: -0.1700
Data Index: 1690887 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.2617. Min Act: -0.1700
Data Index: 5328546 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1992. Min Act: -0.1700
Data Index: 8433556 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1992. Min Act: -0.1700
Data Index: 8657626 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.1367. Min Act: -0.1700
Data Index: 5927646 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.0742. Min Act: -0.1700
Data Index: 6267905 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.0742. Min Act: -0.1700
Data Index: 5853607 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8867. Min Range: -11.8867
Max Act: 11.0742. Min Act: -0.1700
Data Index: 3294329 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19