Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2830 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.5026. Min Act: -0.0000

Data Index: 958399 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.2205. Min Act: 0.0000

Data Index: 81652 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.3301. Min Act: 0.0000

Data Index: 373278 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.2825. Min Act: 0.0000

Data Index: 479824 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.1479. Min Act: -0.0000

Data Index: 41119 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9965. Min Act: -0.0000

Data Index: 1185297 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.1975. Min Act: 0.0000

Data Index: 257179 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.0504. Min Act: 0.0000

Data Index: 478397 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.0269. Min Act: -0.0000

Data Index: 576401 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 2.5026. Min Range: -2.5026

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1198649 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9865. Min Act: -0.0000

Data Index: 908603 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9820. Min Act: 0.0000

Data Index: 562798 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9262. Min Act: -0.0000

Data Index: 704877 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9162. Min Act: 0.0000

Data Index: 1326802 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.9123. Min Act: 0.0000

Data Index: 1317067 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.8916. Min Act: 0.0000

Data Index: 72060 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.8840. Min Act: 0.0000

Data Index: 789432 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.8924. Min Act: 0.0000

Data Index: 1330102 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.8644. Min Act: 0.0000

Data Index: 514722 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 2.5026. Min Range: -2.5026

Max Act: 1.8521. Min Act: 0.0000

Data Index: 913465 (C4 (Web Text))

Max Activating Token Index: 348