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

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

Neuron 1643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.3647. Min Act: -0.0000

Data Index: 226985 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.4870. Min Act: -0.0000

Data Index: 635955 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.2738. Min Act: -0.0000

Data Index: 208436 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.0335. Min Act: -0.0000

Data Index: 598877 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.9783. Min Act: -0.0000

Data Index: 1137121 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.7724. Min Act: -0.0000

Data Index: 1151221 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.0066. Min Act: -0.0000

Data Index: 1296640 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.8584. Min Act: -0.0000

Data Index: 331425 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.9513. Min Act: -0.0000

Data Index: 794023 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.7401. Min Act: -0.0000

Data Index: 3526 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 4.4870. Min Range: -4.4870

Max Act: 4.0446. Min Act: -0.0000

Data Index: 396149 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.5177. Min Act: -0.0000

Data Index: 281599 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.4750. Min Act: -0.0000

Data Index: 76452 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.3369. Min Act: -0.0000

Data Index: 1034289 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.4643. Min Act: -0.0000

Data Index: 697491 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.1621. Min Act: -0.0000

Data Index: 50893 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.4919. Min Act: -0.0000

Data Index: 637393 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.1590. Min Act: -0.0000

Data Index: 798940 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.1635. Min Act: -0.0000

Data Index: 94074 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 4.4870. Min Range: -4.4870

Max Act: 3.1070. Min Act: -0.0000

Data Index: 431028 (C4 (Web Text))

Max Activating Token Index: 768