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

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

Neuron 4555 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1072898 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.1792. Min Act: -0.0000

Data Index: 4019 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.9448. Min Act: -0.0000

Data Index: 991696 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.3375. Min Range: -1.3375

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1081606 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1522588 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8795. Min Act: -0.0000

Data Index: 774162 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8403. Min Act: 0.0000

Data Index: 858910 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8213. Min Act: -0.0000

Data Index: 298450 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8228. Min Act: -0.0000

Data Index: 250782 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1256629 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7762. Min Act: -0.0000

Data Index: 866538 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1567744 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7577. Min Act: -0.0000

Data Index: 1461934 (Python Code)

Max Activating Token Index: 829

Text #13

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1249684 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1636490 (Python Code)

Max Activating Token Index: 715

Text #15

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1403580 (Python Code)

Max Activating Token Index: 472

Text #16

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7331. Min Act: 0.0000

Data Index: 1602141 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1608255 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7312. Min Act: 0.0000

Data Index: 1468451 (Python Code)

Max Activating Token Index: 732

Text #19

Max Range: 1.3375. Min Range: -1.3375

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1154641 (C4 (Web Text))

Max Activating Token Index: 161