Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1978 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5996. Min Act: -0.0000

Data Index: 68115 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1301155 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4501. Min Act: -0.0000

Data Index: 262172 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1078580 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1439548 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4417. Min Act: -0.0000

Data Index: 510216 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3903. Min Act: -0.0000

Data Index: 711201 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1306958 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4330. Min Act: -0.0000

Data Index: 707879 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4191. Min Act: -0.0000

Data Index: 669294 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1570489 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1560148 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4037. Min Act: -0.0000

Data Index: 648624 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1933251 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1814818 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4043. Min Act: -0.0000

Data Index: 648203 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3751. Min Act: -0.0000

Data Index: 699969 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3825. Min Act: -0.0000

Data Index: 230324 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1323413 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.5996. Min Range: -0.5996

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1079095 (The Pile)

Max Activating Token Index: 979