Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1291. Min Range: -5.1291
Max Act: 5.1291. Min Act: -0.1700
Data Index: 4151023 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1291. Min Range: -5.1291
Max Act: 5.0978. Min Act: -0.1700
Data Index: 899758 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1291. Min Range: -5.1291
Max Act: 5.0978. Min Act: -0.1700
Data Index: 3700898 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1291. Min Range: -5.1291
Max Act: 5.0353. Min Act: -0.1700
Data Index: 7985272 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1291. Min Range: -5.1291
Max Act: 5.0666. Min Act: -0.1700
Data Index: 6486269 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.9416. Min Act: -0.1700
Data Index: 4874839 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.9103. Min Act: -0.1700
Data Index: 7514386 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7341061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8791. Min Act: -0.1700
Data Index: 512587 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8791. Min Act: -0.1700
Data Index: 7237908 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8478. Min Act: -0.1700
Data Index: 5531071 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8478. Min Act: -0.1700
Data Index: 2524674 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8166. Min Act: -0.1700
Data Index: 906174 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8478. Min Act: -0.1700
Data Index: 7690116 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.8166. Min Act: -0.1700
Data Index: 8724445 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.7853. Min Act: -0.1700
Data Index: 2483375 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.7853. Min Act: -0.1700
Data Index: 7341205 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.7853. Min Act: -0.1700
Data Index: 3990478 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.7541. Min Act: -0.1700
Data Index: 3640257 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1291. Min Range: -5.1291
Max Act: 4.7853. Min Act: -0.1700
Data Index: 4833609 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19