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

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

Neuron 166 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4935. Min Act: -0.0000

Data Index: 47555 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.4359. Min Act: -0.0000

Data Index: 715219 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3140. Min Act: -0.0000

Data Index: 837597 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.3039. Min Act: -0.0000

Data Index: 266502 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1196130 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2620. Min Act: -0.0000

Data Index: 361510 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2470. Min Act: -0.0000

Data Index: 332277 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2374. Min Act: -0.0000

Data Index: 564171 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1116438 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2380. Min Act: -0.0000

Data Index: 67701 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2427. Min Act: -0.0000

Data Index: 836152 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2244. Min Act: -0.0000

Data Index: 290481 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2415. Min Act: -0.0000

Data Index: 658757 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1144991 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2394. Min Act: -0.0000

Data Index: 142993 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2376. Min Act: -0.0000

Data Index: 803360 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2417. Min Act: -0.0000

Data Index: 266499 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2115. Min Act: -0.0000

Data Index: 8617 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2042. Min Act: -0.0000

Data Index: 399322 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.4935. Min Range: -0.4935

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1319583 (C4 (Web Text))

Max Activating Token Index: 252