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

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

Neuron 2194 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: 0.4002. Min Range: -0.4002

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1446226 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.4002. Min Act: -0.0001

Data Index: 419625 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3766. Min Act: -0.0001

Data Index: 546093 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3300. Min Act: -0.0001

Data Index: 294650 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3854. Min Act: -0.0001

Data Index: 167989 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3444. Min Act: -0.0000

Data Index: 880068 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3460. Min Act: -0.0001

Data Index: 641038 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3404. Min Act: -0.0001

Data Index: 605861 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3014. Min Act: -0.0001

Data Index: 681384 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1650675 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3595. Min Act: -0.0001

Data Index: 1579275 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3282. Min Act: -0.0001

Data Index: 1538478 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1612600 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3492. Min Act: -0.0001

Data Index: 497408 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3529. Min Act: -0.0001

Data Index: 156511 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1336204 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3196. Min Act: -0.0001

Data Index: 152298 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1390029 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3200. Min Act: -0.0000

Data Index: 489081 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.4002. Min Range: -0.4002

Max Act: 0.3380. Min Act: -0.0001

Data Index: 1469317 (Python Code)

Max Activating Token Index: 515