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

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

Neuron 2075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1186623 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.4448. Min Act: -0.0000

Data Index: 276066 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.3685. Min Act: -0.0000

Data Index: 156870 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1180749 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.3450. Min Act: -0.0000

Data Index: 379039 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.3048. Min Act: -0.0000

Data Index: 772469 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1008380 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1230378 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1148004 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1117605 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2540. Min Act: -0.0000

Data Index: 315544 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1198234 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2772. Min Act: -0.0000

Data Index: 56003 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2387. Min Act: -0.0000

Data Index: 184103 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1573118 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1182101 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2267. Min Act: -0.0000

Data Index: 536567 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2428. Min Act: -0.0000

Data Index: 760362 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2221. Min Act: -0.0000

Data Index: 768337 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.5287. Min Range: -0.5287

Max Act: 0.2400. Min Act: -0.0000

Data Index: 58971 (C4 (Web Text))

Max Activating Token Index: 872