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

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

Neuron 4143 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1450. Min Range: -2.1450

Max Act: 2.1450. Min Act: -0.0000

Data Index: 144348 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.6980. Min Act: -0.0000

Data Index: 620819 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1128571 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.6114. Min Act: -0.0000

Data Index: 368681 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.6179. Min Act: -0.0000

Data Index: 1285407 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.4871. Min Act: -0.0000

Data Index: 968481 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3965. Min Act: -0.0000

Data Index: 100796 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.4669. Min Act: -0.0000

Data Index: 356956 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.5302. Min Act: -0.0000

Data Index: 145467 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.4332. Min Act: -0.0000

Data Index: 215950 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3644. Min Act: -0.0000

Data Index: 836082 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3487. Min Act: -0.0000

Data Index: 283229 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1261718 (C4 (Web Text))

Max Activating Token Index: 249

Text #13

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3996. Min Act: -0.0000

Data Index: 686057 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.2503. Min Act: -0.0000

Data Index: 16502 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.4068. Min Act: -0.0000

Data Index: 637092 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1058448 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3638. Min Act: -0.0000

Data Index: 401631 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3698. Min Act: -0.0000

Data Index: 1235251 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 2.1450. Min Range: -2.1450

Max Act: 1.3386. Min Act: -0.0000

Data Index: 153393 (C4 (Web Text))

Max Activating Token Index: 721