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

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

Neuron 3395 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.9870. Min Act: -0.0001

Data Index: 842247 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.9054. Min Act: -0.0001

Data Index: 628055 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.9313. Min Act: -0.0001

Data Index: 1215145 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.8836. Min Act: -0.0001

Data Index: 1005042 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.8451. Min Act: -0.0001

Data Index: 202633 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.8324. Min Act: -0.0001

Data Index: 460429 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7918. Min Act: -0.0001

Data Index: 355247 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7361. Min Act: -0.0001

Data Index: 623540 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7439. Min Act: -0.0001

Data Index: 617338 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7460. Min Act: -0.0001

Data Index: 1180612 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7391. Min Act: -0.0001

Data Index: 802188 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6667. Min Act: -0.0001

Data Index: 699452 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6545. Min Act: -0.0001

Data Index: 373233 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7086. Min Act: -0.0001

Data Index: 354410 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6447. Min Act: -0.0001

Data Index: 549570 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6589. Min Act: -0.0001

Data Index: 703866 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6765. Min Act: -0.0001

Data Index: 678392 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6291. Min Act: -0.0001

Data Index: 704654 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.7178. Min Act: -0.0001

Data Index: 943103 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.9870. Min Range: -0.9870

Max Act: 0.6691. Min Act: -0.0001

Data Index: 112845 (C4 (Web Text))

Max Activating Token Index: 458