Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 65 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2263. Min Range: -8.2263
Max Act: 8.2263. Min Act: -0.1700
Data Index: 4815671 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2263. Min Range: -8.2263
Max Act: 8.1013. Min Act: -0.1700
Data Index: 608581 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.9763. Min Act: -0.1700
Data Index: 5022656 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.9138. Min Act: -0.1700
Data Index: 2066446 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.8513. Min Act: -0.1700
Data Index: 6925483 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.8513. Min Act: -0.1700
Data Index: 5115552 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.7263. Min Act: -0.1700
Data Index: 361933 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.7263. Min Act: -0.1699
Data Index: 7665264 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.7263. Min Act: -0.1700
Data Index: 4395200 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.7888. Min Act: -0.1700
Data Index: 6607642 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6638. Min Act: -0.1700
Data Index: 4131925 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6638. Min Act: -0.1700
Data Index: 4621894 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6013. Min Act: -0.1700
Data Index: 8660265 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6013. Min Act: -0.1700
Data Index: 2905440 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6013. Min Act: -0.1700
Data Index: 6282959 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.6638. Min Act: -0.1700
Data Index: 1006619 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.5388. Min Act: -0.1700
Data Index: 5775507 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.5388. Min Act: -0.1700
Data Index: 3044413 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.5388. Min Act: -0.1700
Data Index: 5841449 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2263. Min Range: -8.2263
Max Act: 7.5388. Min Act: -0.1700
Data Index: 1140641 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19