Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0610. Min Range: -1.0610

Max Act: 1.0610. Min Act: -0.0000

Data Index: 991619 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.9567. Min Act: -0.0000

Data Index: 691153 (C4 (Web Text))

Max Activating Token Index: 401

Text #2

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.8879. Min Act: -0.0000

Data Index: 966763 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.8949. Min Act: -0.0000

Data Index: 580107 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.8827. Min Act: -0.0000

Data Index: 602383 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.8579. Min Act: -0.0000

Data Index: 377530 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1163870 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7804. Min Act: -0.0000

Data Index: 352820 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7104. Min Act: -0.0000

Data Index: 589529 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7460. Min Act: -0.0000

Data Index: 61563 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1179288 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7101. Min Act: -0.0000

Data Index: 509498 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.6817. Min Act: -0.0000

Data Index: 121878 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7028. Min Act: 0.0001

Data Index: 77153 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.6767. Min Act: -0.0000

Data Index: 565128 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7116. Min Act: -0.0000

Data Index: 917973 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1203004 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7038. Min Act: -0.0000

Data Index: 528520 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7268. Min Act: -0.0000

Data Index: 780317 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.0610. Min Range: -1.0610

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1207017 (C4 (Web Text))

Max Activating Token Index: 492