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

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

Neuron 5523 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.4036. Min Act: -0.0000

Data Index: 827371 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3522. Min Act: -0.0000

Data Index: 167319 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1233197 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3280. Min Act: 0.0000

Data Index: 488665 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3332. Min Act: -0.0000

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1202349 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1297178 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3033. Min Act: -0.0000

Data Index: 47480 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2947. Min Act: -0.0000

Data Index: 957191 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.3119. Min Act: -0.0000

Data Index: 697102 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2977. Min Act: -0.0000

Data Index: 519953 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2917. Min Act: -0.0000

Data Index: 74334 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2888. Min Act: -0.0000

Data Index: 908587 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2866. Min Act: -0.0000

Data Index: 992997 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1203727 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2850. Min Act: -0.0000

Data Index: 888142 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1327012 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2738. Min Act: -0.0000

Data Index: 627347 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.4036. Min Range: -0.4036

Max Act: 0.2811. Min Act: -0.0000

Data Index: 295393 (C4 (Web Text))

Max Activating Token Index: 960