Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8098. Min Range: -7.8098
Max Act: 7.8098. Min Act: -0.1700
Data Index: 3248648 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8098. Min Range: -7.8098
Max Act: 7.4973. Min Act: -0.1700
Data Index: 1292956 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8098. Min Range: -7.8098
Max Act: 7.2161. Min Act: -0.1700
Data Index: 3445952 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8098. Min Range: -7.8098
Max Act: 7.1848. Min Act: -0.1700
Data Index: 4536641 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8098. Min Range: -7.8098
Max Act: 7.0911. Min Act: -0.1700
Data Index: 1028847 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.9036. Min Act: -0.1700
Data Index: 2609747 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.8098. Min Act: -0.1700
Data Index: 4568220 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.7786. Min Act: -0.1700
Data Index: 2162630 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.7161. Min Act: -0.1700
Data Index: 8753473 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.6536. Min Act: -0.1700
Data Index: 2213288 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.6223. Min Act: -0.1700
Data Index: 7113576 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.6848. Min Act: -0.1700
Data Index: 1587777 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.6848. Min Act: -0.1700
Data Index: 1030419 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.6223. Min Act: -0.1700
Data Index: 1030414 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5911. Min Act: -0.1700
Data Index: 1030415 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5598. Min Act: -0.1700
Data Index: 6437133 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5598. Min Act: -0.1700
Data Index: 5639429 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5598. Min Act: -0.1700
Data Index: 1030454 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5286. Min Act: -0.1700
Data Index: 4849694 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8098. Min Range: -7.8098
Max Act: 6.5598. Min Act: -0.1700
Data Index: 4620188 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19