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

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

Neuron 46 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1329361 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.3666. Min Act: -0.0000

Data Index: 113742 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1041802 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1232489 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2826. Min Act: -0.0000

Data Index: 771412 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1516464 (Python Code)

Max Activating Token Index: 59

Text #6

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2221. Min Act: -0.0000

Data Index: 228288 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2313. Min Act: -0.0000

Data Index: 20071 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2440. Min Act: -0.0000

Data Index: 749250 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.3016. Min Act: -0.0000

Data Index: 127308 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.2226. Min Act: -0.0000

Data Index: 970891 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.1617. Min Act: -0.0000

Data Index: 361221 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.1360. Min Act: -0.0000

Data Index: 501765 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1652676 (Python Code)

Max Activating Token Index: 121

Text #14

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1032483 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.1025. Min Act: -0.0000

Data Index: 432689 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1208878 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1587552 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.0081. Min Act: -0.0000

Data Index: 38636 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 1.4043. Min Range: -1.4043

Max Act: 1.0514. Min Act: -0.0000

Data Index: 802554 (C4 (Web Text))

Max Activating Token Index: 553