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

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

Neuron 1885 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4700. Min Act: -0.0001

Data Index: 666720 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4344. Min Act: -0.0000

Data Index: 424158 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4125. Min Act: -0.0001

Data Index: 413288 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1039520 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3909. Min Act: -0.0001

Data Index: 613254 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4010. Min Act: -0.0001

Data Index: 946180 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3668. Min Act: -0.0001

Data Index: 1298396 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3814. Min Act: 0.0000

Data Index: 85025 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3717. Min Act: -0.0001

Data Index: 676156 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3835. Min Act: -0.0001

Data Index: 421423 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1146584 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3398. Min Act: -0.0001

Data Index: 373154 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3477. Min Act: -0.0001

Data Index: 86718 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3516. Min Act: -0.0001

Data Index: 1051720 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3479. Min Act: -0.0001

Data Index: 827384 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3334. Min Act: -0.0001

Data Index: 771263 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3343. Min Act: -0.0001

Data Index: 1335701 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1210902 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3241. Min Act: -0.0001

Data Index: 514330 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3219. Min Act: -0.0000

Data Index: 995096 (C4 (Web Text))

Max Activating Token Index: 135