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

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

Neuron 1499 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: 2.7464. Min Range: -2.7464

Max Act: 2.7464. Min Act: -0.0000

Data Index: 302822 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 2.7464. Min Range: -2.7464

Max Act: 2.4928. Min Act: -0.0000

Data Index: 551422 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.7464. Min Range: -2.7464

Max Act: 2.0986. Min Act: -0.0000

Data Index: 990177 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.7464. Min Range: -2.7464

Max Act: 2.0810. Min Act: -0.0000

Data Index: 549126 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 2.7464. Min Range: -2.7464

Max Act: 2.0625. Min Act: -0.0000

Data Index: 265779 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 2.7464. Min Range: -2.7464

Max Act: 2.0546. Min Act: -0.0000

Data Index: 877749 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.9900. Min Act: -0.0000

Data Index: 707654 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.8623. Min Act: -0.0000

Data Index: 332215 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.8198. Min Act: 0.0000

Data Index: 1528820 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.7981. Min Act: -0.0000

Data Index: 424504 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.7621. Min Act: -0.0000

Data Index: 1009287 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.6216. Min Act: -0.0000

Data Index: 272104 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5856. Min Act: -0.0000

Data Index: 1487543 (Python Code)

Max Activating Token Index: 646

Text #13

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5454. Min Act: -0.0000

Data Index: 422199 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5213. Min Act: -0.0000

Data Index: 539771 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.6112. Min Act: -0.0000

Data Index: 1391120 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5059. Min Act: -0.0000

Data Index: 460768 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5028. Min Act: -0.0000

Data Index: 525224 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.6606. Min Act: -0.0000

Data Index: 219207 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.7464. Min Range: -2.7464

Max Act: 1.5669. Min Act: -0.0000

Data Index: 303642 (C4 (Web Text))

Max Activating Token Index: 558