Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1081 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2096. Min Range: -2.2096

Max Act: 2.2096. Min Act: -0.0000

Data Index: 586609 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 2.2096. Min Range: -2.2096

Max Act: 2.1839. Min Act: -0.0000

Data Index: 146450 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 2.2096. Min Range: -2.2096

Max Act: 2.0675. Min Act: -0.0000

Data Index: 269061 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.9176. Min Act: -0.0000

Data Index: 835133 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.8139. Min Act: -0.0000

Data Index: 357754 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.7241. Min Act: -0.0000

Data Index: 878425 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5139. Min Act: -0.0000

Data Index: 295994 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5172. Min Act: -0.0000

Data Index: 734729 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1249423 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5941. Min Act: -0.0000

Data Index: 642387 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1224841 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5554. Min Act: -0.0000

Data Index: 1009648 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5339. Min Act: -0.0000

Data Index: 30814 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.5844. Min Act: -0.0000

Data Index: 897942 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.3328. Min Act: -0.0000

Data Index: 924689 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.4405. Min Act: -0.0000

Data Index: 540331 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1315345 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.4161. Min Act: -0.0000

Data Index: 925090 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.3281. Min Act: -0.0000

Data Index: 114931 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 2.2096. Min Range: -2.2096

Max Act: 1.4072. Min Act: -0.0000

Data Index: 1077316 (C4 (Web Text))

Max Activating Token Index: 929