Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2013 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2896. Min Act: -0.0002

Data Index: 1041189 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2579. Min Act: 0.0003

Data Index: 195194 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2395. Min Act: -0.0002

Data Index: 1103313 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2286. Min Act: -0.0001

Data Index: 836740 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2213. Min Act: -0.0001

Data Index: 382641 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2258. Min Act: -0.0001

Data Index: 262583 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2173. Min Act: -0.0002

Data Index: 986571 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2250. Min Act: 0.0002

Data Index: 753881 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2193. Min Act: -0.0001

Data Index: 223681 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2176. Min Act: 0.0003

Data Index: 1069433 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2174. Min Act: -0.0002

Data Index: 723393 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1113116 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1081684 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2136. Min Act: -0.0001

Data Index: 738402 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2084. Min Act: 0.0003

Data Index: 586719 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2016. Min Act: -0.0002

Data Index: 390006 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2088. Min Act: -0.0002

Data Index: 1021388 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2057. Min Act: -0.0002

Data Index: 569951 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2055. Min Act: -0.0002

Data Index: 935351 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.2896. Min Range: -0.2896

Max Act: 0.2055. Min Act: 0.0003

Data Index: 1272738 (C4 (Web Text))

Max Activating Token Index: 412