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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.6831. Min Act: -0.0000

Data Index: 811780 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5895. Min Act: -0.0000

Data Index: 338063 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1575148 (Python Code)

Max Activating Token Index: 687

Text #3

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5011. Min Act: -0.0000

Data Index: 854159 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5390. Min Act: -0.0000

Data Index: 672706 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5232. Min Act: -0.0000

Data Index: 960685 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1016834 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5505. Min Act: -0.0000

Data Index: 46977 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1054471 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1292339 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1123050 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5163. Min Act: -0.0001

Data Index: 760249 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4938. Min Act: -0.0001

Data Index: 164936 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5082. Min Act: -0.0000

Data Index: 700540 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4884. Min Act: -0.0001

Data Index: 781356 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.5181. Min Act: -0.0000

Data Index: 965456 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1097714 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4965. Min Act: -0.0001

Data Index: 541988 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4921. Min Act: -0.0000

Data Index: 790560 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.6831. Min Range: -0.6831

Max Act: 0.4934. Min Act: -0.0001

Data Index: 1209003 (C4 (Web Text))

Max Activating Token Index: 151