Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.9382. Min Act: -0.1700
Data Index: 532187 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.5945. Min Act: -0.1700
Data Index: 2735217 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.4382. Min Act: -0.1700
Data Index: 961103 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.3132. Min Act: -0.1700
Data Index: 6175041 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.2507. Min Act: -0.1700
Data Index: 756518 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.1882. Min Act: -0.1700
Data Index: 6548783 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.1257. Min Act: -0.1700
Data Index: 2166599 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0945. Min Act: -0.1700
Data Index: 7062693 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0632. Min Act: -0.1700
Data Index: 6058555 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0632. Min Act: -0.1700
Data Index: 6252533 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0320. Min Act: -0.1700
Data Index: 5627890 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0007. Min Act: -0.1700
Data Index: 1482603 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9382. Min Range: -7.9382
Max Act: 7.0632. Min Act: -0.1700
Data Index: 8039370 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9382. Min Act: -0.1700
Data Index: 7585770 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9382. Min Act: -0.1700
Data Index: 5699577 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9070. Min Act: -0.1700
Data Index: 1262089 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9070. Min Act: -0.1700
Data Index: 1649249 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9382. Min Act: -0.1700
Data Index: 452354 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9070. Min Act: -0.1700
Data Index: 1128755 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9382. Min Range: -7.9382
Max Act: 6.9070. Min Act: -0.1700
Data Index: 2996968 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19