Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4816 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 214308 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3042. Min Act: -0.0000

Data Index: 185107 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2920. Min Act: -0.0000

Data Index: 604023 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2944. Min Act: -0.0000

Data Index: 402804 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1236337 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1028203 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2249. Min Act: -0.0000

Data Index: 900469 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1060365 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2132. Min Act: -0.0000

Data Index: 834541 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1973. Min Act: -0.0000

Data Index: 43562 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1345699 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2050. Min Act: -0.0000

Data Index: 911903 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1952. Min Act: -0.0000

Data Index: 99574 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1968. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1914. Min Act: -0.0000

Data Index: 132872 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1089871 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1759. Min Act: -0.0000

Data Index: 839224 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1869. Min Act: -0.0000

Data Index: 478498 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1222947 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.1855. Min Act: -0.0000

Data Index: 511438 (C4 (Web Text))

Max Activating Token Index: 60