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

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

Neuron 2322 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8572. Min Act: -0.0001

Data Index: 792782 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8550. Min Act: -0.0001

Data Index: 1043513 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1271331 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.9010. Min Act: -0.0001

Data Index: 251815 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8571. Min Act: -0.0001

Data Index: 55461 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8481. Min Act: -0.0001

Data Index: 880965 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7854. Min Act: -0.0001

Data Index: 241274 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7298. Min Act: -0.0001

Data Index: 1250631 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7766. Min Act: -0.0001

Data Index: 496634 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8248. Min Act: -0.0001

Data Index: 12541 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7680. Min Act: -0.0001

Data Index: 857559 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6766. Min Act: -0.0001

Data Index: 373909 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7574. Min Act: -0.0001

Data Index: 425107 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.8663. Min Act: -0.0001

Data Index: 330136 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6893. Min Act: -0.0001

Data Index: 267419 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7097. Min Act: -0.0001

Data Index: 1112048 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7394. Min Act: -0.0001

Data Index: 99378 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.7301. Min Act: -0.0001

Data Index: 226170 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6220. Min Act: -0.0001

Data Index: 1008889 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.9010. Min Range: -0.9010

Max Act: 0.6284. Min Act: -0.0001

Data Index: 738492 (C4 (Web Text))

Max Activating Token Index: 667