Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 16 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0006

Data Index: 138784 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0363. Min Act: -0.0006

Data Index: 840783 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0370. Min Act: -0.0006

Data Index: 768521 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1336582 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0356. Min Act: -0.0006

Data Index: 639139 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0342. Min Act: -0.0006

Data Index: 642453 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1326164 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0342. Min Act: -0.0006

Data Index: 1119292 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0326. Min Act: -0.0006

Data Index: 99170 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0006

Data Index: 231312 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1321032 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0314. Min Act: -0.0006

Data Index: 839230 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0328. Min Act: -0.0006

Data Index: 213868 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0320. Min Act: -0.0006

Data Index: 764153 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0333. Min Act: -0.0006

Data Index: 744907 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0326. Min Act: -0.0006

Data Index: 556609 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0318. Min Act: -0.0006

Data Index: 575086 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0338. Min Act: -0.0006

Data Index: 74480 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0327. Min Act: -0.0006

Data Index: 325404 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0319. Min Act: -0.0006

Data Index: 796479 (C4 (Web Text))

Max Activating Token Index: 268