Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4680. Min Act: -0.1700
Data Index: 4071795 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4367. Min Act: -0.1700
Data Index: 3342348 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4055. Min Act: -0.1700
Data Index: 8505390 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4367. Min Act: -0.1700
Data Index: 3635643 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4367. Min Act: -0.1700
Data Index: 4635562 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.4055. Min Act: -0.1700
Data Index: 2099419 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.3742. Min Act: -0.1700
Data Index: 4151057 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.3742. Min Act: -0.1700
Data Index: 8434845 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.3117. Min Act: -0.1700
Data Index: 711417 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.3117. Min Act: -0.1700
Data Index: 2591123 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2805. Min Act: -0.1700
Data Index: 21998 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2492. Min Act: -0.1700
Data Index: 2169059 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2492. Min Act: -0.1700
Data Index: 1365881 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2492. Min Act: -0.1700
Data Index: 6793105 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2180. Min Act: -0.1700
Data Index: 4764027 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.2180. Min Act: -0.1700
Data Index: 2771508 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.1555. Min Act: -0.1700
Data Index: 7056092 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.1867. Min Act: -0.1700
Data Index: 4099720 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.1555. Min Act: -0.1700
Data Index: 1177049 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4680. Min Range: -6.4680
Max Act: 6.1555. Min Act: -0.1700
Data Index: 7656882 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19