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

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

Neuron 3574 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.4172. Min Act: -0.0000

Data Index: 779263 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.4035. Min Act: -0.0000

Data Index: 1273243 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1336349 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3622. Min Act: -0.0000

Data Index: 55594 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3421. Min Act: -0.0000

Data Index: 229652 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3471. Min Act: -0.0000

Data Index: 984666 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1003690 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3145. Min Act: -0.0000

Data Index: 292815 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3209. Min Act: -0.0000

Data Index: 322779 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3145. Min Act: -0.0000

Data Index: 352498 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1245467 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.3021. Min Act: 0.0000

Data Index: 834131 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1340723 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2898. Min Act: -0.0000

Data Index: 952952 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1057515 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2830. Min Act: -0.0000

Data Index: 663261 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1062670 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2681. Min Act: -0.0000

Data Index: 719300 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2661. Min Act: -0.0000

Data Index: 678790 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.4172. Min Range: -0.4172

Max Act: 0.2658. Min Act: -0.0000

Data Index: 442141 (C4 (Web Text))

Max Activating Token Index: 298