Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 800 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.2186. Min Act: -0.0001

Data Index: 303031 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1657. Min Act: -0.0001

Data Index: 458034 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1364. Min Act: -0.0001

Data Index: 1249182 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1150. Min Act: -0.0001

Data Index: 347564 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0424. Min Act: -0.0001

Data Index: 125675 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.1026. Min Act: -0.0001

Data Index: 399440 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0645. Min Act: -0.0001

Data Index: 879197 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1236618 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0656. Min Act: -0.0001

Data Index: 392863 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0396. Min Act: -0.0001

Data Index: 578991 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1112340 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0186. Min Act: -0.0001

Data Index: 991407 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0795. Min Act: -0.0001

Data Index: 529388 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0713. Min Act: -0.0001

Data Index: 584748 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9689. Min Act: -0.0001

Data Index: 1268801 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0362. Min Act: -0.0001

Data Index: 143543 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9920. Min Act: -0.0001

Data Index: 1051676 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9940. Min Act: -0.0001

Data Index: 320618 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.2186. Min Range: -1.2186

Max Act: 0.9627. Min Act: -0.0001

Data Index: 1132231 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 1.2186. Min Range: -1.2186

Max Act: 1.0211. Min Act: -0.0001

Data Index: 890069 (C4 (Web Text))

Max Activating Token Index: 647