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

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

Neuron 1677 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2174. Min Range: -3.2174

Max Act: 3.1264. Min Act: -0.0000

Data Index: 467207 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.2174. Min Range: -3.2174

Max Act: 3.0927. Min Act: -0.0000

Data Index: 209605 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 3.2174. Min Range: -3.2174

Max Act: 3.2174. Min Act: -0.0000

Data Index: 912173 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.9107. Min Act: -0.0000

Data Index: 885768 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.8123. Min Act: -0.0000

Data Index: 342945 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.5935. Min Act: -0.0000

Data Index: 912604 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.1863. Min Act: -0.0000

Data Index: 244751 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.1554. Min Act: -0.0000

Data Index: 665259 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.9594. Min Act: -0.0000

Data Index: 1173945 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.8489. Min Act: -0.0000

Data Index: 876435 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.8150. Min Act: -0.0000

Data Index: 585984 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 3.2174. Min Range: -3.2174

Max Act: 2.0248. Min Act: -0.0000

Data Index: 85150 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.7719. Min Act: -0.0000

Data Index: 981257 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1346311 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1216611 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.7545. Min Act: -0.0000

Data Index: 233570 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.7489. Min Act: -0.0000

Data Index: 906349 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.7051. Min Act: -0.0000

Data Index: 288966 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.6955. Min Act: -0.0000

Data Index: 799546 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.2174. Min Range: -3.2174

Max Act: 1.7932. Min Act: -0.0000

Data Index: 987433 (C4 (Web Text))

Max Activating Token Index: 248