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

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

Neuron 878 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: 2.7704. Min Range: -2.7704

Max Act: 2.6451. Min Act: -0.0000

Data Index: 466648 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.6295. Min Act: -0.0000

Data Index: 706793 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5837. Min Act: -0.0000

Data Index: 191257 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5861. Min Act: -0.0000

Data Index: 264496 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5665. Min Act: -0.0000

Data Index: 339885 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5876. Min Act: -0.0000

Data Index: 595755 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5606. Min Act: -0.0000

Data Index: 873380 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5523. Min Act: -0.0000

Data Index: 535044 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5318. Min Act: -0.0000

Data Index: 392844 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.3948. Min Act: -0.0000

Data Index: 502419 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1346329 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.3486. Min Act: -0.0000

Data Index: 643935 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1227341 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.4430. Min Act: -0.0000

Data Index: 825036 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.4459. Min Act: -0.0000

Data Index: 611134 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.4117. Min Act: -0.0000

Data Index: 39022 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.3820. Min Act: -0.0000

Data Index: 17988 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.2744. Min Act: -0.0000

Data Index: 332077 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.5246. Min Act: -0.0000

Data Index: 139269 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.7704. Min Range: -2.7704

Max Act: 2.3731. Min Act: -0.0000

Data Index: 581373 (C4 (Web Text))

Max Activating Token Index: 782