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

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

Neuron 4845 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: 1.4852. Min Range: -1.4852

Max Act: 1.4852. Min Act: -0.0000

Data Index: 186421 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.2251. Min Act: -0.0000

Data Index: 152570 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.1825. Min Act: -0.0000

Data Index: 784011 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.4852. Min Range: -1.4852

Max Act: 1.0699. Min Act: -0.0000

Data Index: 345437 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1207883 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8961. Min Act: -0.0000

Data Index: 920378 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1146036 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1081062 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8655. Min Act: -0.0000

Data Index: 515965 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8362. Min Act: -0.0000

Data Index: 115635 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.7731. Min Act: -0.0000

Data Index: 609538 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8113. Min Act: -0.0000

Data Index: 232593 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8054. Min Act: -0.0000

Data Index: 535683 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8120. Min Act: -0.0000

Data Index: 782840 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8033. Min Act: -0.0000

Data Index: 565025 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.7931. Min Act: -0.0000

Data Index: 798929 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1261334 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.7769. Min Act: -0.0000

Data Index: 951415 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.8222. Min Act: -0.0000

Data Index: 685357 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 1.4852. Min Range: -1.4852

Max Act: 0.7298. Min Act: -0.0000

Data Index: 1215019 (C4 (Web Text))

Max Activating Token Index: 530