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

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

Neuron 5593 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.3226. Min Act: -0.0000

Data Index: 1648686 (Python Code)

Max Activating Token Index: 910

Text #1

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1017. Min Act: -0.0000

Data Index: 562252 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.9145. Min Act: -0.0000

Data Index: 472976 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.6350. Min Act: -0.0000

Data Index: 498865 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.7837. Min Act: -0.0000

Data Index: 88936 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.5537. Min Act: -0.0000

Data Index: 701239 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.6650. Min Act: -0.0000

Data Index: 904059 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.8116. Min Act: -0.0000

Data Index: 811362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.6469. Min Act: -0.0000

Data Index: 798738 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.6093. Min Act: -0.0000

Data Index: 577461 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.7478. Min Act: -0.0000

Data Index: 729135 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.5683. Min Act: -0.0000

Data Index: 771520 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.5460. Min Act: -0.0000

Data Index: 791251 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.4544. Min Act: -0.0000

Data Index: 973183 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.4694. Min Act: -0.0000

Data Index: 44601 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.5469. Min Act: -0.0000

Data Index: 16191 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.5288. Min Act: -0.0000

Data Index: 571556 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.3348. Min Act: -0.0000

Data Index: 1109193 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.3406. Min Act: -0.0000

Data Index: 344543 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 4.3226. Min Range: -4.3226

Max Act: 3.3068. Min Act: -0.0000

Data Index: 1216692 (C4 (Web Text))

Max Activating Token Index: 756