Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.9616. Min Act: -0.1700
Data Index: 4938157 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.8991. Min Act: -0.1700
Data Index: 7509139 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.8679. Min Act: -0.1700
Data Index: 2521843 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.8054. Min Act: -0.1700
Data Index: 1021810 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.8366. Min Act: -0.1700
Data Index: 8088715 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.8054. Min Act: -0.1700
Data Index: 249798 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.7741. Min Act: -0.1700
Data Index: 7960998 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.7741. Min Act: -0.1700
Data Index: 644198 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.7741. Min Act: -0.1700
Data Index: 7450464 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6804. Min Act: -0.1700
Data Index: 1734613 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8344941 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6491. Min Act: -0.1700
Data Index: 1099032 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.7116. Min Act: -0.1700
Data Index: 628428 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6804. Min Act: -0.1700
Data Index: 4367430 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3893326 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6491. Min Act: -0.1700
Data Index: 7795514 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6491. Min Act: -0.1700
Data Index: 8238063 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6179. Min Act: -0.1700
Data Index: 4777370 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6491. Min Act: -0.1700
Data Index: 6552887 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9616. Min Range: -4.9616
Max Act: 4.6179. Min Act: -0.1700
Data Index: 5139028 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19