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

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

Neuron 2995 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1004670 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3871. Min Act: -0.0000

Data Index: 30389 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3715. Min Act: -0.0000

Data Index: 395688 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3731. Min Act: -0.0000

Data Index: 431188 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3947. Min Act: -0.0000

Data Index: 133359 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3604. Min Act: -0.0000

Data Index: 759078 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3744. Min Act: -0.0000

Data Index: 39253 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3369. Min Act: -0.0000

Data Index: 430347 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3236. Min Act: -0.0000

Data Index: 699070 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3248. Min Act: -0.0000

Data Index: 519368 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3506. Min Act: -0.0000

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3285. Min Act: -0.0000

Data Index: 829288 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3390. Min Act: -0.0001

Data Index: 574768 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3364. Min Act: -0.0000

Data Index: 175727 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3463. Min Act: -0.0000

Data Index: 534844 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3471. Min Act: -0.0000

Data Index: 356237 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3210. Min Act: -0.0000

Data Index: 213121 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3328. Min Act: -0.0000

Data Index: 240662 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1338944 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3128. Min Act: -0.0000

Data Index: 554886 (C4 (Web Text))

Max Activating Token Index: 615