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

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

Neuron 1024 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3694. Min Act: -0.0000

Data Index: 669402 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3086. Min Act: -0.0000

Data Index: 893445 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1205919 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1289048 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2636. Min Act: -0.0000

Data Index: 588944 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2594. Min Act: -0.0000

Data Index: 401866 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2547. Min Act: -0.0000

Data Index: 501509 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2462. Min Act: -0.0000

Data Index: 574636 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2405. Min Act: -0.0000

Data Index: 795451 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2224. Min Act: -0.0000

Data Index: 338417 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2274. Min Act: -0.0000

Data Index: 856277 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1255056 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2211. Min Act: -0.0000

Data Index: 152051 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1157615 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2140. Min Act: -0.0000

Data Index: 143829 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2194. Min Act: -0.0000

Data Index: 282954 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2118. Min Act: -0.0000

Data Index: 841696 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2127. Min Act: -0.0000

Data Index: 388120 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2156. Min Act: -0.0000

Data Index: 566845 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1109652 (C4 (Web Text))

Max Activating Token Index: 397