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

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

Neuron 1962 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.3144. Min Act: -0.0000

Data Index: 263026 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1040301 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2978. Min Act: -0.0000

Data Index: 606505 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2782. Min Act: -0.0000

Data Index: 377654 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2586. Min Act: -0.0000

Data Index: 158364 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1072765 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1324519 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1240204 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1279320 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2333. Min Act: -0.0000

Data Index: 661457 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2531. Min Act: -0.0000

Data Index: 780510 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2383. Min Act: -0.0000

Data Index: 788542 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2604. Min Act: -0.0000

Data Index: 712696 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2136. Min Act: -0.0000

Data Index: 728809 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2285. Min Act: -0.0000

Data Index: 412965 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1139610 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2286. Min Act: -0.0000

Data Index: 220100 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2369. Min Act: -0.0000

Data Index: 975219 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1076974 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.3144. Min Range: -0.3144

Max Act: 0.2090. Min Act: -0.0000

Data Index: 681876 (C4 (Web Text))

Max Activating Token Index: 389