Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1027 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.7158. Min Act: -0.0001
Data Index: 1262722 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.5138. Min Act: -0.0001
Data Index: 1548777 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.5917. Min Act: -0.0001
Data Index: 354976 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.4007. Min Act: -0.0001
Data Index: 883247 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.2750. Min Act: -0.0001
Data Index: 664822 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.3265. Min Act: -0.0001
Data Index: 1071187 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.3550. Min Act: -0.0001
Data Index: 583473 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.3427. Min Act: -0.0001
Data Index: 454050 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1811. Min Act: -0.0001
Data Index: 1040610 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1402. Min Act: -0.0001
Data Index: 223560 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1372. Min Act: -0.0001
Data Index: 163402 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.0774. Min Act: -0.0001
Data Index: 341541 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1486. Min Act: -0.0001
Data Index: 223305 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1111. Min Act: -0.0001
Data Index: 999081 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.0990. Min Act: -0.0001
Data Index: 1330703 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1621. Min Act: -0.0001
Data Index: 134795 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1631. Min Act: -0.0001
Data Index: 824225 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.3032. Min Act: -0.0001
Data Index: 1223315 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7158. Min Range: -1.7158
Max Act: 1.1429. Min Act: -0.0001
Data Index: 1832597 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7158. Min Range: -1.7158
Max Act: 0.9887. Min Act: -0.0001
Data Index: 1984206 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19