Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3166 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.3385. Min Act: -0.0000

Data Index: 240372 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2916. Min Act: -0.0000

Data Index: 828030 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2883. Min Act: -0.0000

Data Index: 821324 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2825. Min Act: -0.0000

Data Index: 351290 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1291726 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2599. Min Act: -0.0000

Data Index: 311484 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1124556 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1438570 (Python Code)

Max Activating Token Index: 533

Text #8

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2642. Min Act: -0.0000

Data Index: 423838 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2913. Min Act: -0.0000

Data Index: 977136 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2639. Min Act: 0.0000

Data Index: 1251240 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1160672 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2668. Min Act: 0.0000

Data Index: 1239423 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1137855 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2548. Min Act: -0.0000

Data Index: 983894 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2538. Min Act: -0.0000

Data Index: 1528053 (Python Code)

Max Activating Token Index: 688

Text #16

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2528. Min Act: -0.0000

Data Index: 928781 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2532. Min Act: -0.0000

Data Index: 762319 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1460448 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.3385. Min Range: -0.3385

Max Act: 0.2511. Min Act: -0.0000

Data Index: 777130 (C4 (Web Text))

Max Activating Token Index: 487