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

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

Neuron 1670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.6868. Min Act: -0.0000

Data Index: 938819 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.6713. Min Act: -0.0001

Data Index: 671254 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.5979. Min Act: -0.0000

Data Index: 988727 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4738. Min Act: -0.0001

Data Index: 700250 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4471. Min Act: -0.0001

Data Index: 1100723 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1132301 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4156. Min Act: -0.0001

Data Index: 1234320 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.4081. Min Act: -0.0000

Data Index: 426578 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.3332. Min Act: -0.0000

Data Index: 876158 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.3208. Min Act: -0.0001

Data Index: 578530 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2973. Min Act: -0.0000

Data Index: 492830 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2890. Min Act: -0.0000

Data Index: 175636 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.3194. Min Act: -0.0001

Data Index: 697859 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2777. Min Act: -0.0000

Data Index: 316028 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2785. Min Act: -0.0000

Data Index: 1284809 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1053755 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2658. Min Act: -0.0001

Data Index: 270068 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.1808. Min Act: -0.0000

Data Index: 1221460 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.2106. Min Act: -0.0001

Data Index: 215919 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.6868. Min Range: -1.6868

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1032707 (C4 (Web Text))

Max Activating Token Index: 644