Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2684. Min Act: -0.0003

Data Index: 1167876 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.3079. Min Act: -0.0003

Data Index: 209904 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2209. Min Act: -0.0003

Data Index: 1238731 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2969. Min Act: -0.0003

Data Index: 800974 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2566. Min Act: -0.0003

Data Index: 716096 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1863. Min Act: -0.0003

Data Index: 79008 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2425. Min Act: -0.0003

Data Index: 727087 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.2255. Min Act: -0.0003

Data Index: 460186 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1859. Min Act: -0.0003

Data Index: 1293298 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0103. Min Act: -0.0003

Data Index: 844196 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1683. Min Act: -0.0003

Data Index: 243141 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1044. Min Act: -0.0003

Data Index: 1288839 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1641. Min Act: -0.0003

Data Index: 1128053 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.3079. Min Range: -1.3079

Max Act: 0.9708. Min Act: -0.0003

Data Index: 167551 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0378. Min Act: -0.0003

Data Index: 1000891 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0738. Min Act: -0.0003

Data Index: 526304 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 1.3079. Min Range: -1.3079

Max Act: 0.9694. Min Act: -0.0003

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.3079. Min Range: -1.3079

Max Act: 0.9791. Min Act: -0.0003

Data Index: 68124 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.1248. Min Act: -0.0003

Data Index: 905999 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.3079. Min Range: -1.3079

Max Act: 1.0953. Min Act: -0.0003

Data Index: 847312 (C4 (Web Text))

Max Activating Token Index: 129