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

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

Neuron 3710 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.3045. Min Act: -0.0000

Data Index: 918966 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.9769. Min Act: -0.0000

Data Index: 185485 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.8775. Min Act: -0.0000

Data Index: 1302332 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.8475. Min Act: -0.0000

Data Index: 1068702 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.9830. Min Act: -0.0000

Data Index: 883980 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 4.3045. Min Range: -4.3045

Max Act: 3.2314. Min Act: -0.0000

Data Index: 205921 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.4667. Min Act: -0.0000

Data Index: 422662 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1222920 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.2472. Min Act: -0.0000

Data Index: 1113375 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.5039. Min Act: -0.0000

Data Index: 820666 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.2254. Min Act: -0.0000

Data Index: 1254861 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.3280. Min Act: -0.0000

Data Index: 302660 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 4.3045. Min Range: -4.3045

Max Act: 1.9544. Min Act: -0.0000

Data Index: 689840 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.2244. Min Act: -0.0000

Data Index: 798608 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.1706. Min Act: -0.0000

Data Index: 944797 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.1094. Min Act: -0.0000

Data Index: 449402 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.0949. Min Act: -0.0000

Data Index: 1240480 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.0743. Min Act: -0.0000

Data Index: 530753 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 4.3045. Min Range: -4.3045

Max Act: 2.0911. Min Act: -0.0000

Data Index: 618830 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 4.3045. Min Range: -4.3045

Max Act: 1.9588. Min Act: -0.0000

Data Index: 418330 (C4 (Web Text))

Max Activating Token Index: 924