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

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

Neuron 2247 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2834. Min Act: -0.0001

Data Index: 762874 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2768. Min Act: -0.0000

Data Index: 956060 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2634. Min Act: -0.0000

Data Index: 197585 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2466. Min Act: -0.0001

Data Index: 751837 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2566. Min Act: -0.0001

Data Index: 754958 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1243726 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2270. Min Act: -0.0000

Data Index: 562886 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2176. Min Act: -0.0000

Data Index: 350830 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2263. Min Act: -0.0000

Data Index: 514415 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2233. Min Act: -0.0000

Data Index: 997552 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2142. Min Act: -0.0001

Data Index: 201200 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2345. Min Act: -0.0001

Data Index: 20781 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2206. Min Act: -0.0000

Data Index: 7690 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2280. Min Act: -0.0000

Data Index: 593087 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2053. Min Act: -0.0000

Data Index: 694516 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2157. Min Act: -0.0000

Data Index: 468164 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.2834. Min Range: -0.2834

Max Act: 0.2080. Min Act: -0.0000

Data Index: 854591 (C4 (Web Text))

Max Activating Token Index: 214