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

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

Neuron 2 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: 5.1107. Min Range: -5.1107

Max Act: 5.1107. Min Act: -0.0000

Data Index: 333480 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 5.1107. Min Range: -5.1107

Max Act: 4.1047. Min Act: -0.0000

Data Index: 637726 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 5.1107. Min Range: -5.1107

Max Act: 4.0398. Min Act: -0.0000

Data Index: 140059 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 5.1107. Min Range: -5.1107

Max Act: 3.5330. Min Act: -0.0000

Data Index: 929430 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.8043. Min Act: -0.0001

Data Index: 679124 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.7653. Min Act: -0.0000

Data Index: 521925 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.6136. Min Act: -0.0000

Data Index: 1217546 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.6821. Min Act: -0.0000

Data Index: 480165 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.5733. Min Act: -0.0000

Data Index: 383462 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.7067. Min Act: -0.0001

Data Index: 1046822 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.4677. Min Act: -0.0001

Data Index: 978515 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.2597. Min Act: -0.0000

Data Index: 624637 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.3493. Min Act: -0.0000

Data Index: 1319185 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.3028. Min Act: -0.0001

Data Index: 103661 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.2816. Min Act: -0.0000

Data Index: 27831 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.3231. Min Act: -0.0000

Data Index: 24976 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.0532. Min Act: -0.0000

Data Index: 179671 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.4105. Min Act: -0.0000

Data Index: 1179308 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 5.1107. Min Range: -5.1107

Max Act: 2.1686. Min Act: -0.0000

Data Index: 1243491 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 5.1107. Min Range: -5.1107

Max Act: 1.9882. Min Act: -0.0000

Data Index: 877382 (C4 (Web Text))

Max Activating Token Index: 218