Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.3175. Min Act: -0.0001

Data Index: 1215737 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.7484. Min Act: -0.0001

Data Index: 89058 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.7080. Min Act: -0.0001

Data Index: 1336943 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.4199. Min Act: -0.0001

Data Index: 226656 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.3211. Min Act: -0.0001

Data Index: 218635 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.2866. Min Act: -0.0000

Data Index: 1184852 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.4346. Min Act: -0.0001

Data Index: 847084 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.9120. Min Act: -0.0001

Data Index: 433296 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.1298. Min Act: -0.0001

Data Index: 314407 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.9701. Min Act: -0.0000

Data Index: 1354647 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.8412. Min Act: -0.0001

Data Index: 1072275 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 3.3175. Min Range: -3.3175

Max Act: 2.0361. Min Act: -0.0001

Data Index: 7501 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.9171. Min Act: -0.0001

Data Index: 906093 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.8876. Min Act: -0.0001

Data Index: 508349 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.7597. Min Act: -0.0001

Data Index: 570972 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.7918. Min Act: -0.0001

Data Index: 616289 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.7775. Min Act: -0.0001

Data Index: 71271 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.7609. Min Act: -0.0001

Data Index: 1320995 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.9539. Min Act: -0.0001

Data Index: 890262 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 3.3175. Min Range: -3.3175

Max Act: 1.6048. Min Act: -0.0001

Data Index: 1283652 (C4 (Web Text))

Max Activating Token Index: 678