Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3114 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.7407. Min Act: -0.1700
Data Index: 654756 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.6157. Min Act: -0.1700
Data Index: 7329713 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.4595. Min Act: -0.1700
Data Index: 5750294 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.4282. Min Act: -0.1700
Data Index: 6717832 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.4907. Min Act: -0.1700
Data Index: 2878031 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.3657. Min Act: -0.1700
Data Index: 821942 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.4282. Min Act: -0.1700
Data Index: 795120 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.3032. Min Act: -0.1700
Data Index: 95017 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.2095. Min Act: -0.1700
Data Index: 6628647 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.2095. Min Act: -0.1700
Data Index: 6479969 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.2407. Min Act: -0.1700
Data Index: 6514460 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1782. Min Act: -0.1700
Data Index: 763800 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1782. Min Act: -0.1700
Data Index: 2852661 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1157. Min Act: -0.1700
Data Index: 7380805 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1157. Min Act: -0.1700
Data Index: 4416701 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1157. Min Act: -0.1700
Data Index: 6884731 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1157. Min Act: -0.1700
Data Index: 3012982 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.1157. Min Act: -0.1700
Data Index: 6151073 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.0532. Min Act: -0.1700
Data Index: 4963171 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7407. Min Range: -7.7407
Max Act: 7.0845. Min Act: -0.1700
Data Index: 7884509 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19