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

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

Neuron 4429 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0496. Min Range: -2.0496

Max Act: 2.0496. Min Act: -0.0002

Data Index: 1183683 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9746. Min Act: -0.0002

Data Index: 442665 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.8814. Min Act: -0.0002

Data Index: 509747 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7724. Min Act: -0.0002

Data Index: 1291406 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7679. Min Act: -0.0002

Data Index: 1274036 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7619. Min Act: -0.0002

Data Index: 926438 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7554. Min Act: -0.0002

Data Index: 531545 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7446. Min Act: -0.0002

Data Index: 354057 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.7416. Min Act: -0.0002

Data Index: 736255 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6933. Min Act: -0.0002

Data Index: 745738 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6797. Min Act: -0.0002

Data Index: 15945 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6048. Min Act: -0.0002

Data Index: 696069 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6388. Min Act: -0.0002

Data Index: 670326 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6513. Min Act: -0.0002

Data Index: 1054862 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6223. Min Act: -0.0002

Data Index: 1293947 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6441. Min Act: -0.0002

Data Index: 400321 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6120. Min Act: -0.0002

Data Index: 836019 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.5906. Min Act: -0.0002

Data Index: 901265 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6020. Min Act: -0.0002

Data Index: 986598 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.6336. Min Act: -0.0002

Data Index: 1299098 (C4 (Web Text))

Max Activating Token Index: 381