Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.2277. Min Act: -0.1700
Data Index: 6997813 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.2277. Min Act: -0.1700
Data Index: 862784 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.1339. Min Act: -0.1700
Data Index: 8394316 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.1339. Min Act: -0.1700
Data Index: 4696777 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6283336 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.1027. Min Act: -0.1700
Data Index: 6309033 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.1027. Min Act: -0.1700
Data Index: 7996786 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4304371 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 1422460 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4751544 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 567440 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4696776 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 4401710 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 3150546 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 858869 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0714. Min Act: -0.1700
Data Index: 8642732 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0402. Min Act: -0.1700
Data Index: 6218520 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0402. Min Act: -0.1700
Data Index: 3988158 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0402. Min Act: -0.1700
Data Index: 8721397 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2277. Min Range: -5.2277
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7787471 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19