Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3401 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.9308. Min Act: -0.1700
Data Index: 4191724 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.7121. Min Act: -0.1700
Data Index: 4838036 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.6808. Min Act: -0.1700
Data Index: 5458454 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.5871. Min Act: -0.1700
Data Index: 209892 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.5871. Min Act: -0.1700
Data Index: 4320765 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.5558. Min Act: -0.1700
Data Index: 6760999 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.5246. Min Act: -0.1700
Data Index: 8667279 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3463053 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.4308. Min Act: -0.1700
Data Index: 4010498 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.4621. Min Act: -0.1700
Data Index: 3502991 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3996. Min Act: -0.1700
Data Index: 6995001 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3996. Min Act: -0.1700
Data Index: 447287 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3996. Min Act: -0.1700
Data Index: 2393166 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3996. Min Act: -0.1700
Data Index: 963369 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3683. Min Act: -0.1700
Data Index: 4965099 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3683. Min Act: -0.1700
Data Index: 2932229 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3683. Min Act: -0.1700
Data Index: 6633525 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3371. Min Act: -0.1700
Data Index: 7604833 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3371. Min Act: -0.1700
Data Index: 6951105 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9308. Min Range: -6.9308
Max Act: 6.3058. Min Act: -0.1700
Data Index: 485716 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19