Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 633 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.3342. Min Act: -0.0001

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.0453. Min Act: -0.0001

Data Index: 899597 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.1089. Min Act: -0.0001

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9760. Min Act: -0.0001

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.0448. Min Act: -0.0001

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.1106. Min Act: -0.0001

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9818. Min Act: -0.0001

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 3.3342. Min Range: -3.3342

Max Act: 3.1030. Min Act: -0.0001

Data Index: 468505 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9438. Min Act: -0.0001

Data Index: 813743 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9285. Min Act: -0.0001

Data Index: 1357112 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9098. Min Act: -0.0001

Data Index: 486726 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.7974. Min Act: -0.0001

Data Index: 1063169 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.7763. Min Act: -0.0001

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.8949. Min Act: -0.0001

Data Index: 234010 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.9816. Min Act: -0.0001

Data Index: 702828 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.6526. Min Act: -0.0001

Data Index: 410186 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.5818. Min Act: -0.0001

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.6594. Min Act: -0.0001

Data Index: 165459 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.5266. Min Act: -0.0001

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 3.3342. Min Range: -3.3342

Max Act: 2.6258. Min Act: -0.0001

Data Index: 617817 (C4 (Web Text))

Max Activating Token Index: 373