Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0367. Min Act: -0.0005

Data Index: 694488 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0005

Data Index: 632721 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0368. Min Act: -0.0005

Data Index: 700004 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0342. Min Act: -0.0005

Data Index: 1050401 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0344. Min Act: -0.0005

Data Index: 32856 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0334. Min Act: -0.0005

Data Index: 296205 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0330. Min Act: -0.0005

Data Index: 1320432 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0338. Min Act: -0.0005

Data Index: 846690 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0327. Min Act: -0.0005

Data Index: 336419 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0325. Min Act: -0.0005

Data Index: 831628 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0320. Min Act: -0.0005

Data Index: 261125 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0328. Min Act: -0.0005

Data Index: 865563 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0326. Min Act: -0.0005

Data Index: 176941 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1173944 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0310. Min Act: -0.0005

Data Index: 336971 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0319. Min Act: -0.0005

Data Index: 874430 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0312. Min Act: -0.0005

Data Index: 1256175 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0313. Min Act: -0.0005

Data Index: 84599 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0325. Min Act: -0.0005

Data Index: 958300 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1179728 (C4 (Web Text))

Max Activating Token Index: 335