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

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

Neuron 876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.8228. Min Act: -0.0001

Data Index: 1295814 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.6714. Min Act: -0.0001

Data Index: 761630 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.5142. Min Act: -0.0001

Data Index: 172008 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.2875. Min Act: -0.0001

Data Index: 1110070 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.3634. Min Act: -0.0001

Data Index: 1310763 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9386. Min Act: -0.0001

Data Index: 1045992 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9812. Min Act: -0.0001

Data Index: 115920 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.0374. Min Act: -0.0001

Data Index: 1036254 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9042. Min Act: -0.0001

Data Index: 343166 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9930. Min Act: -0.0001

Data Index: 884310 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.1257. Min Act: -0.0001

Data Index: 131947 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9227. Min Act: -0.0001

Data Index: 135510 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.9180. Min Act: -0.0001

Data Index: 200654 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 3.8228. Min Range: -3.8228

Max Act: 3.1885. Min Act: -0.0001

Data Index: 18863 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.5148. Min Act: -0.0001

Data Index: 474149 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.7935. Min Act: -0.0001

Data Index: 996813 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.7852. Min Act: -0.0001

Data Index: 615572 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.7583. Min Act: -0.0001

Data Index: 402665 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.7249. Min Act: -0.0001

Data Index: 1137436 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.8228. Min Range: -3.8228

Max Act: 2.7282. Min Act: -0.0001

Data Index: 744740 (C4 (Web Text))

Max Activating Token Index: 513