Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1708. Min Range: -7.1708
Max Act: 7.1708. Min Act: -0.1700
Data Index: 6186059 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1708. Min Range: -7.1708
Max Act: 7.1395. Min Act: -0.1700
Data Index: 5996587 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1708. Min Range: -7.1708
Max Act: 7.0770. Min Act: -0.1700
Data Index: 1107827 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.8895. Min Act: -0.1700
Data Index: 3003875 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.8583. Min Act: -0.1700
Data Index: 7627941 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.7333. Min Act: -0.1700
Data Index: 2316741 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.7020. Min Act: -0.1700
Data Index: 7091908 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.4833. Min Act: -0.1700
Data Index: 8477635 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3895. Min Act: -0.1700
Data Index: 879620 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3270. Min Act: -0.1700
Data Index: 816935 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3895. Min Act: -0.1700
Data Index: 4895282 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.2645. Min Act: -0.1700
Data Index: 8134691 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3270. Min Act: -0.1700
Data Index: 6869305 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3270. Min Act: -0.1700
Data Index: 6600322 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3583. Min Act: -0.1700
Data Index: 4989607 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.3270. Min Act: -0.1700
Data Index: 4087140 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.2645. Min Act: -0.1700
Data Index: 7398434 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.2645. Min Act: -0.1700
Data Index: 4264950 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.1708. Min Act: -0.1700
Data Index: 2920543 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1708. Min Range: -7.1708
Max Act: 6.2333. Min Act: -0.1700
Data Index: 5896953 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19