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

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

Neuron 2035 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2225. Min Range: -4.2225

Max Act: 4.0058. Min Act: -0.0000

Data Index: 305772 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.8921. Min Act: -0.0000

Data Index: 1289679 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 4.2225. Min Range: -4.2225

Max Act: 4.2225. Min Act: -0.0000

Data Index: 307974 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.9297. Min Act: -0.0000

Data Index: 1252156 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.9305. Min Act: -0.0000

Data Index: 766576 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.9039. Min Act: -0.0000

Data Index: 816181 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 4.2225. Min Range: -4.2225

Max Act: 4.0762. Min Act: -0.0000

Data Index: 697556 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.8595. Min Act: -0.0000

Data Index: 313831 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.7023. Min Act: -0.0000

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.7044. Min Act: -0.0000

Data Index: 1300982 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.5005. Min Act: -0.0000

Data Index: 1042910 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1318130 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.5898. Min Act: -0.0000

Data Index: 698911 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.7327. Min Act: -0.0000

Data Index: 76613 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.4171. Min Act: -0.0000

Data Index: 1336558 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.5584. Min Act: -0.0000

Data Index: 966739 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.5470. Min Act: -0.0000

Data Index: 857004 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.3800. Min Act: -0.0000

Data Index: 1221925 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.3586. Min Act: -0.0000

Data Index: 31514 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 4.2225. Min Range: -4.2225

Max Act: 3.6656. Min Act: -0.0000

Data Index: 652815 (C4 (Web Text))

Max Activating Token Index: 665