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

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

Neuron 5623 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7582. Min Act: -0.0000

Data Index: 165155 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1061792 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1094387 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7103. Min Act: -0.0000

Data Index: 118449 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6490. Min Act: -0.0000

Data Index: 622141 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1063848 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1146831 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1210692 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6211. Min Act: -0.0000

Data Index: 735683 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5697. Min Act: -0.0000

Data Index: 102027 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.6222. Min Act: -0.0000

Data Index: 643485 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1231072 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5946. Min Act: -0.0000

Data Index: 22388 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5790. Min Act: -0.0000

Data Index: 712887 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5274. Min Act: -0.0000

Data Index: 559196 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5633. Min Act: -0.0000

Data Index: 621389 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1305949 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5597. Min Act: -0.0000

Data Index: 881237 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5817. Min Act: -0.0000

Data Index: 763066 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 0.7705. Min Range: -0.7705

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1079632 (C4 (Web Text))

Max Activating Token Index: 328