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

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

Neuron 5284 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2979. Min Act: -0.0001

Data Index: 860899 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2821. Min Act: -0.0000

Data Index: 52608 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2695. Min Act: -0.0001

Data Index: 124233 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2788. Min Act: -0.0001

Data Index: 453275 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2653. Min Act: -0.0000

Data Index: 126343 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2610. Min Act: -0.0000

Data Index: 909622 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2653. Min Act: -0.0001

Data Index: 334092 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2544. Min Act: -0.0000

Data Index: 351518 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2526. Min Act: -0.0001

Data Index: 30630 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2513. Min Act: -0.0001

Data Index: 169447 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2406. Min Act: -0.0001

Data Index: 219190 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2538. Min Act: -0.0001

Data Index: 783130 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2524. Min Act: -0.0001

Data Index: 678611 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2395. Min Act: -0.0000

Data Index: 502393 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2280. Min Act: -0.0000

Data Index: 972622 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2631. Min Act: -0.0000

Data Index: 190352 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2522. Min Act: -0.0001

Data Index: 639799 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2151. Min Act: -0.0000

Data Index: 497208 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2392. Min Act: -0.0000

Data Index: 551514 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.2979. Min Range: -0.2979

Max Act: 0.2142. Min Act: -0.0001

Data Index: 645178 (C4 (Web Text))

Max Activating Token Index: 286