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

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

Neuron 160 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: 0.3567. Min Range: -0.3567

Max Act: 0.3567. Min Act: -0.0003

Data Index: 737756 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3123. Min Act: -0.0003

Data Index: 760563 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3156. Min Act: -0.0003

Data Index: 1312675 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3283. Min Act: -0.0003

Data Index: 666197 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2304. Min Act: -0.0003

Data Index: 270787 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3064. Min Act: -0.0003

Data Index: 214849 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3110. Min Act: -0.0003

Data Index: 214769 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3105. Min Act: -0.0003

Data Index: 157316 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2762. Min Act: -0.0003

Data Index: 314163 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3062. Min Act: -0.0003

Data Index: 1105388 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2759. Min Act: -0.0003

Data Index: 1226162 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3276. Min Act: -0.0003

Data Index: 1214425 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2927. Min Act: -0.0003

Data Index: 708023 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2599. Min Act: -0.0003

Data Index: 56405 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2610. Min Act: -0.0003

Data Index: 1019596 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2967. Min Act: -0.0003

Data Index: 636779 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2995. Min Act: -0.0003

Data Index: 162438 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2641. Min Act: -0.0003

Data Index: 1293837 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2963. Min Act: -0.0003

Data Index: 791792 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2946. Min Act: -0.0003

Data Index: 1011955 (C4 (Web Text))

Max Activating Token Index: 500