Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2680 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0886. Min Range: -3.0886

Max Act: 3.0886. Min Act: -0.0000

Data Index: 652734 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.8282. Min Act: -0.0001

Data Index: 1039240 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.8963. Min Act: -0.0001

Data Index: 504854 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.6147. Min Act: -0.0000

Data Index: 686506 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.5245. Min Act: -0.0000

Data Index: 94980 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.2086. Min Act: -0.0001

Data Index: 707914 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.3084. Min Act: -0.0000

Data Index: 816413 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1150324 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.2536. Min Act: -0.0001

Data Index: 705356 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.3456. Min Act: -0.0000

Data Index: 32979 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.9110. Min Act: -0.0001

Data Index: 197415 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.1040. Min Act: -0.0001

Data Index: 161726 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.2229. Min Act: -0.0000

Data Index: 94307 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.4290. Min Act: -0.0001

Data Index: 1185028 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.2716. Min Act: -0.0000

Data Index: 819023 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 3.0886. Min Range: -3.0886

Max Act: 1.8332. Min Act: -0.0001

Data Index: 510532 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.0383. Min Act: -0.0001

Data Index: 589226 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.1392. Min Act: -0.0000

Data Index: 1025224 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.0154. Min Act: -0.0000

Data Index: 471429 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 3.0886. Min Range: -3.0886

Max Act: 2.1041. Min Act: -0.0000

Data Index: 744950 (C4 (Web Text))

Max Activating Token Index: 524