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

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

Neuron 287 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: 3.5240. Min Range: -3.5240

Max Act: 3.4532. Min Act: -0.0000

Data Index: 412653 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 3.5240. Min Range: -3.5240

Max Act: 3.5240. Min Act: -0.0000

Data Index: 991749 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.9530. Min Act: -0.0000

Data Index: 692855 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.7073. Min Act: -0.0000

Data Index: 791461 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.5338. Min Act: -0.0000

Data Index: 39314 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.5336. Min Act: -0.0000

Data Index: 1169098 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.6439. Min Act: -0.0000

Data Index: 302322 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.6319. Min Act: -0.0000

Data Index: 416164 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.2467. Min Act: -0.0000

Data Index: 1202700 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.3070. Min Act: -0.0000

Data Index: 1165455 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.3588. Min Act: -0.0000

Data Index: 951873 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.1964. Min Act: -0.0000

Data Index: 309553 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.1627. Min Act: -0.0000

Data Index: 192594 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 3.5240. Min Range: -3.5240

Max Act: 1.9617. Min Act: -0.0000

Data Index: 497077 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.1280. Min Act: -0.0000

Data Index: 926298 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.5240. Min Range: -3.5240

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1017132 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.1691. Min Act: -0.0000

Data Index: 519466 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 3.5240. Min Range: -3.5240

Max Act: 1.9067. Min Act: -0.0000

Data Index: 1008506 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 3.5240. Min Range: -3.5240

Max Act: 1.9177. Min Act: -0.0000

Data Index: 758054 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 3.5240. Min Range: -3.5240

Max Act: 2.0335. Min Act: -0.0000

Data Index: 1332746 (C4 (Web Text))

Max Activating Token Index: 7