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

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

Neuron 4019 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.8359. Min Act: -0.0000

Data Index: 1102729 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.6504. Min Act: -0.0000

Data Index: 747720 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.5779. Min Act: -0.0000

Data Index: 1058943 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.4475. Min Act: -0.0000

Data Index: 630577 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.4255. Min Act: -0.0000

Data Index: 149879 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1691. Min Act: -0.0001

Data Index: 632627 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.4837. Min Act: -0.0000

Data Index: 750500 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.3942. Min Act: -0.0000

Data Index: 308804 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.3695. Min Act: -0.0001

Data Index: 642565 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.3819. Min Act: -0.0000

Data Index: 865413 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1356. Min Act: -0.0001

Data Index: 1305333 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1177. Min Act: -0.0000

Data Index: 876824 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.0150. Min Act: -0.0000

Data Index: 34032 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.2023. Min Act: -0.0000

Data Index: 1041898 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1989. Min Act: -0.0000

Data Index: 817321 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1912. Min Act: -0.0000

Data Index: 1210525 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.0716. Min Act: -0.0000

Data Index: 982499 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.2614. Min Act: -0.0001

Data Index: 58275 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1937. Min Act: -0.0000

Data Index: 477051 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 2.8359. Min Range: -2.8359

Max Act: 2.1068. Min Act: -0.0001

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 329