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

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

Neuron 2130 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: 0.4156. Min Range: -0.4156

Max Act: 0.4156. Min Act: -0.0001

Data Index: 171575 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.3632. Min Act: -0.0001

Data Index: 869998 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2841. Min Act: -0.0001

Data Index: 1059707 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2891. Min Act: -0.0001

Data Index: 128383 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1006438 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2825. Min Act: -0.0001

Data Index: 386259 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2784. Min Act: -0.0001

Data Index: 894872 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2634. Min Act: -0.0001

Data Index: 39774 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2634. Min Act: -0.0001

Data Index: 579575 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2785. Min Act: -0.0001

Data Index: 475419 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2543. Min Act: -0.0001

Data Index: 408147 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2450. Min Act: -0.0001

Data Index: 543207 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2356. Min Act: -0.0001

Data Index: 72891 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2473. Min Act: -0.0001

Data Index: 316509 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2232. Min Act: -0.0001

Data Index: 705477 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2366. Min Act: -0.0001

Data Index: 142464 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2274. Min Act: -0.0001

Data Index: 308094 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2521. Min Act: -0.0001

Data Index: 677468 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2333. Min Act: -0.0001

Data Index: 480091 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.4156. Min Range: -0.4156

Max Act: 0.2322. Min Act: -0.0001

Data Index: 205953 (C4 (Web Text))

Max Activating Token Index: 266