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

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

Neuron 4305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1184543 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7160. Min Act: -0.0000

Data Index: 256009 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7298. Min Act: -0.0000

Data Index: 948124 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.7084. Min Act: -0.0000

Data Index: 969197 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6723. Min Act: -0.0000

Data Index: 810679 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1011625 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6862. Min Act: -0.0000

Data Index: 499383 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6307. Min Act: -0.0001

Data Index: 663494 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6165. Min Act: -0.0000

Data Index: 186211 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6249. Min Act: -0.0000

Data Index: 705425 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.6158. Min Act: -0.0000

Data Index: 591367 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5912. Min Act: -0.0000

Data Index: 131110 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5816. Min Act: -0.0000

Data Index: 616545 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5780. Min Act: -0.0000

Data Index: 631297 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5339. Min Act: -0.0000

Data Index: 568471 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5656. Min Act: -0.0000

Data Index: 222067 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1273432 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1087168 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5593. Min Act: -0.0000

Data Index: 542416 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.7633. Min Range: -0.7633

Max Act: 0.5725. Min Act: -0.0000

Data Index: 975722 (C4 (Web Text))

Max Activating Token Index: 952