Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4056 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1272. Min Act: -0.0002

Data Index: 908147 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1043675 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1081935 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1154. Min Act: -0.0002

Data Index: 807235 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1066. Min Act: -0.0002

Data Index: 250488 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1029. Min Act: -0.0002

Data Index: 712170 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1015. Min Act: -0.0002

Data Index: 498500 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0996. Min Act: -0.0002

Data Index: 279873 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0963. Min Act: -0.0002

Data Index: 751475 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0900. Min Act: -0.0002

Data Index: 96297 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0904. Min Act: -0.0002

Data Index: 365169 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0946. Min Act: -0.0002

Data Index: 851196 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1308441 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0947. Min Act: -0.0002

Data Index: 24772 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0924. Min Act: -0.0002

Data Index: 266557 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0907. Min Act: -0.0002

Data Index: 25654 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0886. Min Act: -0.0002

Data Index: 668351 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1169770 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0844. Min Act: -0.0002

Data Index: 301607 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0922. Min Act: -0.0002

Data Index: 817613 (C4 (Web Text))

Max Activating Token Index: 225