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

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

Neuron 3640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4716. Min Range: -2.4716

Max Act: 2.4716. Min Act: -0.0000

Data Index: 762674 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 2.4716. Min Range: -2.4716

Max Act: 2.3629. Min Act: -0.0000

Data Index: 916197 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 2.4716. Min Range: -2.4716

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1344935 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 2.4716. Min Range: -2.4716

Max Act: 2.1115. Min Act: -0.0000

Data Index: 446884 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.7583. Min Act: -0.0001

Data Index: 219840 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.5200. Min Act: -0.0000

Data Index: 909070 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.5176. Min Act: -0.0000

Data Index: 158031 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.4000. Min Act: -0.0000

Data Index: 768896 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3547. Min Act: -0.0000

Data Index: 149897 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.2966. Min Act: -0.0000

Data Index: 338677 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3814. Min Act: -0.0001

Data Index: 171966 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.2093. Min Act: -0.0000

Data Index: 519928 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3023. Min Act: -0.0000

Data Index: 906354 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1169750 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3221. Min Act: -0.0000

Data Index: 966386 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3350. Min Act: -0.0000

Data Index: 1138170 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3155. Min Act: -0.0000

Data Index: 621752 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.3170. Min Act: -0.0000

Data Index: 910164 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.2803. Min Act: -0.0000

Data Index: 389641 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 2.4716. Min Range: -2.4716

Max Act: 1.2409. Min Act: -0.0000

Data Index: 316969 (C4 (Web Text))

Max Activating Token Index: 112