Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8631. Min Act: -0.1700
Data Index: 353623 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8006. Min Act: -0.1700
Data Index: 2551642 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7850. Min Act: -0.1700
Data Index: 4824710 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7850. Min Act: -0.1700
Data Index: 7593136 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7850. Min Act: -0.1700
Data Index: 3571633 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7850. Min Act: -0.1700
Data Index: 8708071 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.8006. Min Act: -0.1700
Data Index: 1765092 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7380. Min Act: -0.1700
Data Index: 7458629 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7224. Min Act: -0.1700
Data Index: 6909865 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7224. Min Act: -0.1700
Data Index: 8322208 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7224. Min Act: -0.1700
Data Index: 494983 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7224. Min Act: -0.1700
Data Index: 8720207 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.7224. Min Act: -0.1700
Data Index: 952982 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6755. Min Act: -0.1700
Data Index: 6144108 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6911. Min Act: -0.1700
Data Index: 8479599 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6755. Min Act: -0.1700
Data Index: 3104225 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6911. Min Act: -0.1700
Data Index: 8659291 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6755. Min Act: -0.1700
Data Index: 1991732 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6598. Min Act: -0.1700
Data Index: 1580603 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8631. Min Range: -3.8631
Max Act: 3.6442. Min Act: -0.1700
Data Index: 248475 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19