Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2012 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0003

Data Index: 53347 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0555. Min Act: -0.0003

Data Index: 67870 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0462. Min Act: -0.0003

Data Index: 776497 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1298659 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0426. Min Act: -0.0003

Data Index: 58335 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0488. Min Act: -0.0003

Data Index: 366680 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0426. Min Act: -0.0003

Data Index: 69780 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0444. Min Act: -0.0003

Data Index: 260086 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0402. Min Act: -0.0003

Data Index: 265575 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0430. Min Act: -0.0003

Data Index: 504552 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0400. Min Act: -0.0003

Data Index: 176517 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0421. Min Act: -0.0003

Data Index: 914159 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0426. Min Act: -0.0003

Data Index: 755389 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0437. Min Act: -0.0003

Data Index: 846622 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1319150 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0443. Min Act: -0.0003

Data Index: 406117 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0432. Min Act: -0.0003

Data Index: 295304 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1299582 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0003

Data Index: 733956 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0406. Min Act: -0.0003

Data Index: 115912 (C4 (Web Text))

Max Activating Token Index: 427