Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2030 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2563. Min Act: -0.0002
Data Index: 620257 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2257. Min Act: -0.0002
Data Index: 856182 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2254. Min Act: -0.0002
Data Index: 1294358 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2231. Min Act: -0.0002
Data Index: 361786 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2136. Min Act: -0.0002
Data Index: 528379 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2084. Min Act: -0.0002
Data Index: 1299258 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2166. Min Act: -0.0002
Data Index: 263300 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2169. Min Act: -0.0002
Data Index: 131093 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2079. Min Act: -0.0002
Data Index: 312588 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2123. Min Act: -0.0002
Data Index: 376124 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2035. Min Act: -0.0002
Data Index: 891261 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2027. Min Act: -0.0002
Data Index: 1222642 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2007. Min Act: -0.0002
Data Index: 199439 (C4 (Web Text))
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1969. Min Act: -0.0002
Data Index: 99860 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.2039. Min Act: -0.0002
Data Index: 313194 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1972. Min Act: -0.0002
Data Index: 672501 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1965. Min Act: -0.0002
Data Index: 594299 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1930. Min Act: -0.0002
Data Index: 558949 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1924. Min Act: -0.0002
Data Index: 843198 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2563. Min Range: -0.2563
Max Act: 0.1986. Min Act: -0.0002
Data Index: 856344 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19