Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1276 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 366788 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2987. Min Act: -0.0000

Data Index: 524865 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2963. Min Act: -0.0000

Data Index: 653128 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2931. Min Act: -0.0000

Data Index: 557095 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1251366 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2687. Min Act: -0.0000

Data Index: 345773 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2741. Min Act: -0.0000

Data Index: 78136 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1244562 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1137215 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2542. Min Act: -0.0000

Data Index: 235044 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1016203 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2510. Min Act: -0.0000

Data Index: 775144 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2443. Min Act: -0.0000

Data Index: 503592 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2286. Min Act: -0.0000

Data Index: 378947 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2446. Min Act: -0.0000

Data Index: 921359 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2417. Min Act: -0.0000

Data Index: 34674 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2295. Min Act: -0.0000

Data Index: 966332 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1237214 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1269081 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2240. Min Act: -0.0000

Data Index: 456733 (C4 (Web Text))

Max Activating Token Index: 681