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

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

Neuron 837 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.1612. Min Act: -0.0001

Data Index: 1262009 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.3055. Min Act: -0.0001

Data Index: 1166472 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.0163. Min Act: -0.0002

Data Index: 1032192 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.2131. Min Act: -0.0002

Data Index: 853573 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.0569. Min Act: -0.0002

Data Index: 94079 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7891. Min Act: -0.0001

Data Index: 263310 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7156. Min Act: -0.0001

Data Index: 756921 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.9972. Min Act: -0.0001

Data Index: 598879 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 3.3055. Min Range: -3.3055

Max Act: 3.2087. Min Act: -0.0001

Data Index: 626196 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7601. Min Act: -0.0002

Data Index: 700867 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.8529. Min Act: -0.0001

Data Index: 606044 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7278. Min Act: -0.0002

Data Index: 1122480 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.8001. Min Act: -0.0002

Data Index: 1209664 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.4207. Min Act: -0.0002

Data Index: 522375 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.4205. Min Act: -0.0001

Data Index: 318389 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7484. Min Act: -0.0002

Data Index: 663585 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.6370. Min Act: -0.0002

Data Index: 64995 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7013. Min Act: -0.0002

Data Index: 442483 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.7640. Min Act: -0.0002

Data Index: 354255 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.3055. Min Range: -3.3055

Max Act: 2.8486. Min Act: -0.0001

Data Index: 1302154 (C4 (Web Text))

Max Activating Token Index: 461