Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1977 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0433. Min Act: -0.0006

Data Index: 895430 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1169831 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0432. Min Act: -0.0006

Data Index: 491772 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0426. Min Act: -0.0005

Data Index: 735678 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0412. Min Act: -0.0006

Data Index: 938233 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0401. Min Act: -0.0006

Data Index: 650072 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1096811 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0385. Min Act: -0.0006

Data Index: 303972 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1124555 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0373. Min Act: -0.0006

Data Index: 294067 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0380. Min Act: -0.0006

Data Index: 580984 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0339. Min Act: -0.0006

Data Index: 1136396 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0399. Min Act: -0.0006

Data Index: 11176 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0357. Min Act: -0.0006

Data Index: 910103 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0371. Min Act: -0.0006

Data Index: 1344124 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0360. Min Act: -0.0006

Data Index: 189654 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0357. Min Act: -0.0006

Data Index: 413243 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0358. Min Act: -0.0006

Data Index: 500012 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0351. Min Act: -0.0006

Data Index: 983042 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0358. Min Act: -0.0006

Data Index: 831389 (C4 (Web Text))

Max Activating Token Index: 319