Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 318 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4339. Min Act: -0.0001
Data Index: 1891482 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4160. Min Act: -0.0001
Data Index: 403341 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4077. Min Act: -0.0001
Data Index: 1028724 (The Pile)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4227. Min Act: -0.0001
Data Index: 778383 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4084. Min Act: -0.0001
Data Index: 1594563 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4026. Min Act: -0.0001
Data Index: 371404 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4232. Min Act: -0.0001
Data Index: 124075 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4150. Min Act: -0.0001
Data Index: 1921254 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4071. Min Act: -0.0001
Data Index: 110092 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3979. Min Act: -0.0001
Data Index: 236774 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4063. Min Act: -0.0001
Data Index: 730205 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3921. Min Act: -0.0001
Data Index: 1418417 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.4044. Min Act: -0.0001
Data Index: 1150348 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3890. Min Act: -0.0001
Data Index: 1524504 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3913. Min Act: -0.0001
Data Index: 679491 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3743. Min Act: -0.0001
Data Index: 830223 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3881. Min Act: -0.0001
Data Index: 1372001 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3862. Min Act: -0.0001
Data Index: 638852 (The Pile)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3835. Min Act: -0.0001
Data Index: 1763471 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4339. Min Range: -0.4339
Max Act: 0.3976. Min Act: -0.0001
Data Index: 1853528 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19