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

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

Neuron 1830 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: 3.9549. Min Range: -3.9549

Max Act: 3.9549. Min Act: -0.0000

Data Index: 721983 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.2042. Min Act: -0.0000

Data Index: 1317381 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.3339. Min Act: -0.0000

Data Index: 1164122 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.7350. Min Act: -0.0000

Data Index: 310730 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.3279. Min Act: -0.0000

Data Index: 237272 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.0387. Min Act: -0.0001

Data Index: 1116507 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.1180. Min Act: -0.0000

Data Index: 632347 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.1905. Min Act: -0.0000

Data Index: 18888 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.0134. Min Act: -0.0000

Data Index: 696618 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.9150. Min Act: -0.0000

Data Index: 1348172 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 3.9549. Min Range: -3.9549

Max Act: 3.0235. Min Act: -0.0000

Data Index: 1359663 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.8673. Min Act: -0.0000

Data Index: 826231 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.8788. Min Act: -0.0000

Data Index: 1058935 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.6275. Min Act: -0.0000

Data Index: 819404 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.7325. Min Act: -0.0000

Data Index: 696912 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.8484. Min Act: -0.0000

Data Index: 567833 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.6938. Min Act: -0.0000

Data Index: 1061692 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.9520. Min Act: -0.0001

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.5219. Min Act: -0.0000

Data Index: 838025 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 3.9549. Min Range: -3.9549

Max Act: 2.5153. Min Act: -0.0001

Data Index: 1651929 (Python Code)

Max Activating Token Index: 718