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

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

Neuron 1920 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0422. Min Act: -0.0006

Data Index: 348344 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0373. Min Act: -0.0006

Data Index: 56974 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0353. Min Act: -0.0006

Data Index: 540818 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0357. Min Act: -0.0006

Data Index: 90157 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0369. Min Act: -0.0006

Data Index: 767896 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0334. Min Act: -0.0006

Data Index: 114842 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0330. Min Act: -0.0006

Data Index: 163664 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1089026 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0344. Min Act: -0.0006

Data Index: 136215 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0292. Min Act: -0.0006

Data Index: 423926 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0321. Min Act: -0.0006

Data Index: 689223 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0315. Min Act: -0.0006

Data Index: 236462 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0307. Min Act: -0.0006

Data Index: 34976 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0320. Min Act: -0.0006

Data Index: 23941 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0326. Min Act: -0.0006

Data Index: 273061 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0325. Min Act: -0.0006

Data Index: 463650 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0312. Min Act: -0.0006

Data Index: 646095 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0298. Min Act: -0.0006

Data Index: 739681 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0323. Min Act: -0.0006

Data Index: 602677 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.0422. Min Range: -0.0422

Max Act: 0.0323. Min Act: -0.0006

Data Index: 1084327 (C4 (Web Text))

Max Activating Token Index: 389