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

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

Neuron 2393 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.9424. Min Act: -0.0001

Data Index: 1031640 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.7275. Min Act: -0.0000

Data Index: 234306 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6978. Min Act: -0.0001

Data Index: 1115039 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.7440. Min Act: -0.0001

Data Index: 338632 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6187. Min Act: -0.0001

Data Index: 249884 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6555. Min Act: -0.0001

Data Index: 1342174 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6369. Min Act: -0.0000

Data Index: 619488 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1268246 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4716. Min Act: -0.0001

Data Index: 513191 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4674. Min Act: -0.0001

Data Index: 186022 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4304. Min Act: -0.0001

Data Index: 1252064 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1224704 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4270. Min Act: -0.0001

Data Index: 305429 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.5387. Min Act: -0.0001

Data Index: 708168 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.5295. Min Act: -0.0000

Data Index: 6200 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.5415. Min Act: -0.0000

Data Index: 1088680 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4425. Min Act: -0.0001

Data Index: 364218 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.6139. Min Act: -0.0001

Data Index: 290419 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.4794. Min Act: -0.0000

Data Index: 408227 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.9424. Min Range: -1.9424

Max Act: 1.3715. Min Act: -0.0000

Data Index: 909086 (C4 (Web Text))

Max Activating Token Index: 706