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

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

Neuron 5870 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.9635. Min Act: -0.0000

Data Index: 782991 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 2.1923. Min Range: -2.1923

Max Act: 2.1923. Min Act: -0.0000

Data Index: 245385 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 2.1923. Min Range: -2.1923

Max Act: 2.1018. Min Act: -0.0000

Data Index: 429248 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.9065. Min Act: -0.0000

Data Index: 253306 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.8196. Min Act: -0.0000

Data Index: 116488 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.6941. Min Act: -0.0000

Data Index: 568319 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.7697. Min Act: -0.0000

Data Index: 1222510 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.7580. Min Act: -0.0000

Data Index: 510320 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.5641. Min Act: -0.0000

Data Index: 920970 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.8337. Min Act: -0.0000

Data Index: 1194483 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1173609 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.7075. Min Act: -0.0000

Data Index: 239114 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.7101. Min Act: -0.0000

Data Index: 320682 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.6582. Min Act: -0.0000

Data Index: 34209 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.5520. Min Act: -0.0000

Data Index: 846012 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.6143. Min Act: -0.0000

Data Index: 650622 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.5734. Min Act: -0.0000

Data Index: 624184 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.7587. Min Act: -0.0000

Data Index: 336606 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.5442. Min Act: -0.0000

Data Index: 284966 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.1923. Min Range: -2.1923

Max Act: 1.5500. Min Act: -0.0000

Data Index: 748228 (C4 (Web Text))

Max Activating Token Index: 56