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

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

Neuron 6068 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: 0.5728. Min Range: -0.5728

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1133700 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1133122 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.5569. Min Act: -0.0000

Data Index: 533837 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4785. Min Act: -0.0000

Data Index: 273641 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4893. Min Act: -0.0000

Data Index: 247374 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4966. Min Act: -0.0000

Data Index: 429327 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4649. Min Act: -0.0000

Data Index: 51332 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4648. Min Act: -0.0000

Data Index: 941844 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4647. Min Act: -0.0000

Data Index: 842713 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4241. Min Act: -0.0000

Data Index: 815240 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.4204. Min Act: -0.0000

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3815. Min Act: -0.0000

Data Index: 515480 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3200. Min Act: -0.0000

Data Index: 370807 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2999. Min Act: -0.0000

Data Index: 978032 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2872. Min Act: -0.0000

Data Index: 195216 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2714. Min Act: -0.0000

Data Index: 217595 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2517. Min Act: -0.0000

Data Index: 449237 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2669. Min Act: -0.0000

Data Index: 687112 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.5728. Min Range: -0.5728

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 70