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

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

Neuron 4600 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.6428. Min Act: -0.0000

Data Index: 318355 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.8481. Min Act: -0.0000

Data Index: 90431 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.6817. Min Act: -0.0000

Data Index: 181402 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.6840. Min Act: -0.0000

Data Index: 898578 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.5572. Min Act: -0.0000

Data Index: 914848 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.5406. Min Act: -0.0000

Data Index: 93959 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.5268. Min Act: -0.0000

Data Index: 903342 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.4009. Min Act: -0.0000

Data Index: 10654 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.5030. Min Act: -0.0000

Data Index: 451282 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.3777. Min Act: -0.0000

Data Index: 410430 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.4682. Min Act: -0.0000

Data Index: 540924 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.4438. Min Act: -0.0000

Data Index: 557618 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.3786. Min Act: -0.0000

Data Index: 552678 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.3944. Min Act: -0.0000

Data Index: 300223 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.2200. Min Act: -0.0000

Data Index: 456580 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.3174. Min Act: -0.0000

Data Index: 1148555 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.3252. Min Act: -0.0000

Data Index: 475718 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.1242. Min Act: -0.0000

Data Index: 603003 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.2413. Min Act: -0.0000

Data Index: 984325 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 2.8481. Min Range: -2.8481

Max Act: 2.2243. Min Act: -0.0000

Data Index: 1174851 (C4 (Web Text))

Max Activating Token Index: 324