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

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

Neuron 211 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6602. Min Act: -0.0003

Data Index: 1270026 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6968. Min Act: -0.0003

Data Index: 1127202 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6250. Min Act: -0.0003

Data Index: 280700 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6552. Min Act: -0.0003

Data Index: 903169 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5828. Min Act: -0.0003

Data Index: 706227 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5982. Min Act: -0.0003

Data Index: 75970 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6123. Min Act: -0.0003

Data Index: 336886 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6036. Min Act: -0.0003

Data Index: 1329965 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6038. Min Act: -0.0003

Data Index: 1170780 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5658. Min Act: -0.0003

Data Index: 1232327 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5567. Min Act: -0.0003

Data Index: 217336 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5983. Min Act: -0.0003

Data Index: 637486 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.6006. Min Act: -0.0003

Data Index: 807991 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5285. Min Act: -0.0003

Data Index: 1077187 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5484. Min Act: -0.0003

Data Index: 1048178 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5449. Min Act: -0.0003

Data Index: 1227123 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.4924. Min Act: -0.0003

Data Index: 633236 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5548. Min Act: -0.0003

Data Index: 765909 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5381. Min Act: -0.0003

Data Index: 1320248 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.6968. Min Range: -0.6968

Max Act: 0.5180. Min Act: -0.0003

Data Index: 503090 (C4 (Web Text))

Max Activating Token Index: 887