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

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

Neuron 502 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.7775. Min Act: -0.0000

Data Index: 939205 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.5660. Min Act: -0.0000

Data Index: 454500 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.5543. Min Act: -0.0000

Data Index: 515321 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.5345. Min Act: -0.0000

Data Index: 56706 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4672. Min Act: -0.0000

Data Index: 1284932 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4484. Min Act: -0.0000

Data Index: 1073387 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4589. Min Act: -0.0000

Data Index: 1332377 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1317751 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.5289. Min Act: -0.0000

Data Index: 58308 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.3902. Min Act: -0.0000

Data Index: 1329111 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.6583. Min Act: -0.0000

Data Index: 802514 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.5131. Min Act: -0.0000

Data Index: 139511 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.3438. Min Act: -0.0000

Data Index: 997667 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4956. Min Act: -0.0000

Data Index: 195267 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.4607. Min Act: -0.0000

Data Index: 479663 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.3298. Min Act: -0.0000

Data Index: 69743 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.3209. Min Act: -0.0000

Data Index: 26195 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.3271. Min Act: -0.0000

Data Index: 152176 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.2933. Min Act: -0.0000

Data Index: 826913 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.7775. Min Range: -2.7775

Max Act: 2.2836. Min Act: -0.0000

Data Index: 76915 (C4 (Web Text))

Max Activating Token Index: 348