Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2295 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3509. Min Act: -0.0001

Data Index: 335932 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3436. Min Act: -0.0001

Data Index: 521043 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1026894 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2972. Min Act: -0.0001

Data Index: 843379 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2985. Min Act: -0.0001

Data Index: 1233884 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3032. Min Act: -0.0001

Data Index: 804017 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3049. Min Act: -0.0001

Data Index: 473258 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3006. Min Act: -0.0001

Data Index: 371791 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3186. Min Act: -0.0001

Data Index: 1212144 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1169390 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2852. Min Act: -0.0001

Data Index: 1055988 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2981. Min Act: -0.0001

Data Index: 139262 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2787. Min Act: -0.0001

Data Index: 1110221 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2798. Min Act: -0.0001

Data Index: 419050 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1313564 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2701. Min Act: -0.0001

Data Index: 123792 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1133444 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2559. Min Act: -0.0001

Data Index: 1298020 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2815. Min Act: -0.0001

Data Index: 737878 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.3509. Min Range: -0.3509

Max Act: 0.2824. Min Act: -0.0001

Data Index: 103657 (C4 (Web Text))

Max Activating Token Index: 57