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

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

Neuron 1539 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.7839. Min Act: -0.0001

Data Index: 738763 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.8319. Min Act: -0.0001

Data Index: 949474 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.7904. Min Act: -0.0001

Data Index: 141342 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.6813. Min Act: -0.0001

Data Index: 230704 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.7467. Min Act: -0.0001

Data Index: 65683 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.4715. Min Act: -0.0001

Data Index: 724941 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.6307. Min Act: -0.0001

Data Index: 681472 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.7211. Min Act: -0.0001

Data Index: 204612 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.6638. Min Act: -0.0001

Data Index: 1064706 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.5552. Min Act: -0.0001

Data Index: 135842 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.5362. Min Act: -0.0001

Data Index: 589725 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.5233. Min Act: -0.0001

Data Index: 1100942 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.6152. Min Act: -0.0001

Data Index: 1235218 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.5781. Min Act: -0.0001

Data Index: 542616 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.4856. Min Act: -0.0001

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.3888. Min Act: -0.0001

Data Index: 613425 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.3492. Min Act: -0.0001

Data Index: 472535 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.4508. Min Act: -0.0001

Data Index: 336447 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.4449. Min Act: -0.0001

Data Index: 465278 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.8319. Min Range: -1.8319

Max Act: 1.4213. Min Act: -0.0001

Data Index: 75669 (C4 (Web Text))

Max Activating Token Index: 166