Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9621. Min Range: -6.9621
Max Act: 6.9621. Min Act: -0.1700
Data Index: 2886480 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9621. Min Range: -6.9621
Max Act: 6.1184. Min Act: -0.1700
Data Index: 5755459 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9621. Min Range: -6.9621
Max Act: 6.0246. Min Act: -0.1700
Data Index: 262920 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.9934. Min Act: -0.1700
Data Index: 8564791 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9621. Min Range: -6.9621
Max Act: 6.0246. Min Act: -0.1700
Data Index: 5774716 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.9621. Min Act: -0.1700
Data Index: 7089272 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.8371. Min Act: -0.1700
Data Index: 8724827 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.8996. Min Act: -0.1700
Data Index: 5410018 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.8059. Min Act: -0.1700
Data Index: 3159937 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.8059. Min Act: -0.1700
Data Index: 3097393 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.7434. Min Act: -0.1700
Data Index: 4785910 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.7434. Min Act: -0.1700
Data Index: 151256 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.7746. Min Act: -0.1700
Data Index: 3255908 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6809. Min Act: -0.1700
Data Index: 4298842 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6809. Min Act: -0.1700
Data Index: 4579502 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6809. Min Act: -0.1700
Data Index: 1578975 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6496. Min Act: -0.1700
Data Index: 4389898 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.5871. Min Act: -0.1700
Data Index: 6189076 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6184. Min Act: -0.1700
Data Index: 2412963 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9621. Min Range: -6.9621
Max Act: 5.6496. Min Act: -0.1700
Data Index: 7666733 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19