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

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

Neuron 137 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0470. Min Act: -0.0002

Data Index: 247811 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0442. Min Act: -0.0002

Data Index: 161261 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1196102 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1288475 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0418. Min Act: -0.0002

Data Index: 712809 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0415. Min Act: -0.0002

Data Index: 217407 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1219189 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1099352 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0406. Min Act: -0.0002

Data Index: 423892 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0413. Min Act: -0.0002

Data Index: 363556 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0002

Data Index: 589919 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0404. Min Act: -0.0002

Data Index: 431675 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1242987 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0397. Min Act: -0.0002

Data Index: 159257 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1351623 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0395. Min Act: -0.0002

Data Index: 516272 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0392. Min Act: -0.0002

Data Index: 236638 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0384. Min Act: -0.0002

Data Index: 964431 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0390. Min Act: -0.0002

Data Index: 155339 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0470. Min Range: -0.0470

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1184432 (C4 (Web Text))

Max Activating Token Index: 923