Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1315 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.4866. Min Act: -0.1700
Data Index: 1241142 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.3616. Min Act: -0.1700
Data Index: 6157129 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.3616. Min Act: -0.1700
Data Index: 1960976 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.2991. Min Act: -0.1700
Data Index: 7148324 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.3616. Min Act: -0.1700
Data Index: 7306944 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.2366. Min Act: -0.1700
Data Index: 1257633 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.1741. Min Act: -0.1700
Data Index: 2053016 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.2366. Min Act: -0.1700
Data Index: 2159364 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.1116. Min Act: -0.1700
Data Index: 3246415 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.1116. Min Act: -0.1700
Data Index: 7826594 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.1741. Min Act: -0.1700
Data Index: 351810 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4866. Min Range: -9.4866
Max Act: 9.0491. Min Act: -0.1700
Data Index: 5906136 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9866. Min Act: -0.1700
Data Index: 1340350 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9866. Min Act: -0.1700
Data Index: 4743760 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9866. Min Act: -0.1700
Data Index: 843395 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9241. Min Act: -0.1700
Data Index: 7441820 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9241. Min Act: -0.1700
Data Index: 5067600 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9241. Min Act: -0.1700
Data Index: 7691254 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.9241. Min Act: -0.1700
Data Index: 2815918 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4866. Min Range: -9.4866
Max Act: 8.8616. Min Act: -0.1700
Data Index: 6096882 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19