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

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

Neuron 3857 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: 0.7347. Min Range: -0.7347

Max Act: 0.7347. Min Act: -0.0000

Data Index: 360803 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6769. Min Act: -0.0000

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1236744 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6352. Min Act: -0.0000

Data Index: 672828 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1268853 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1261096 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5841. Min Act: -0.0000

Data Index: 975185 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5615. Min Act: -0.0000

Data Index: 81780 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5795. Min Act: -0.0000

Data Index: 317592 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.6133. Min Act: -0.0000

Data Index: 564373 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5675. Min Act: -0.0000

Data Index: 608490 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5631. Min Act: -0.0000

Data Index: 320980 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5437. Min Act: -0.0000

Data Index: 749314 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5484. Min Act: -0.0000

Data Index: 407664 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1302365 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5157. Min Act: -0.0000

Data Index: 405872 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5238. Min Act: -0.0000

Data Index: 252404 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1192635 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.4800. Min Act: -0.0000

Data Index: 886438 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 0.7347. Min Range: -0.7347

Max Act: 0.5170. Min Act: -0.0000

Data Index: 441493 (C4 (Web Text))

Max Activating Token Index: 779