Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1594 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.2336. Min Range: -5.2336

Max Act: 5.2336. Min Act: -0.0001

Data Index: 1230213 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 5.2336. Min Range: -5.2336

Max Act: 5.0332. Min Act: -0.0001

Data Index: 189660 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.8129. Min Act: -0.0001

Data Index: 263336 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.7783. Min Act: -0.0001

Data Index: 310804 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.8017. Min Act: -0.0001

Data Index: 564672 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.8758. Min Act: -0.0001

Data Index: 944164 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.8447. Min Act: -0.0001

Data Index: 708123 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.9560. Min Act: -0.0001

Data Index: 1029038 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.7103. Min Act: -0.0001

Data Index: 1235402 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.7078. Min Act: -0.0001

Data Index: 526187 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.6097. Min Act: -0.0001

Data Index: 115720 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.5821. Min Act: -0.0001

Data Index: 243511 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.4086. Min Act: -0.0001

Data Index: 1110524 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.4521. Min Act: -0.0001

Data Index: 795356 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.2627. Min Act: -0.0001

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.3442. Min Act: -0.0001

Data Index: 498158 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 5.2336. Min Range: -5.2336

Max Act: 3.9760. Min Act: -0.0001

Data Index: 786028 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.3103. Min Act: -0.0001

Data Index: 931567 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.1399. Min Act: -0.0001

Data Index: 230590 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 5.2336. Min Range: -5.2336

Max Act: 4.1383. Min Act: -0.0001

Data Index: 450773 (C4 (Web Text))

Max Activating Token Index: 989