Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1317 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1858. Min Act: -0.0001
Data Index: 426438 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2277. Min Act: -0.0001
Data Index: 257119 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2166. Min Act: -0.0001
Data Index: 1669490 (The Pile)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2112. Min Act: -0.0001
Data Index: 779998 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2166. Min Act: -0.0001
Data Index: 331683 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2108. Min Act: -0.0001
Data Index: 1090912 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2094. Min Act: -0.0001
Data Index: 636243 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1815. Min Act: -0.0001
Data Index: 366710 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2083. Min Act: -0.0001
Data Index: 436993 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1914. Min Act: -0.0001
Data Index: 1275308 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1987. Min Act: -0.0001
Data Index: 1763880 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1431. Min Act: -0.0001
Data Index: 1238003 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2040. Min Act: -0.0001
Data Index: 1896663 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1898. Min Act: -0.0001
Data Index: 1003397 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1959. Min Act: -0.0001
Data Index: 480383 (The Pile)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1723. Min Act: -0.0001
Data Index: 361552 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.2222. Min Act: -0.0001
Data Index: 1457327 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1985. Min Act: -0.0001
Data Index: 200069 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1849. Min Act: -0.0001
Data Index: 447389 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2277. Min Range: -0.2277
Max Act: 0.1717. Min Act: -0.0001
Data Index: 1935289 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19