Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1233 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.5236. Min Act: -0.0001

Data Index: 978010 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.8422. Min Act: -0.0001

Data Index: 726924 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 4.0077. Min Range: -4.0077

Max Act: 4.0077. Min Act: -0.0001

Data Index: 1241796 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.7963. Min Act: -0.0001

Data Index: 606469 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.4120. Min Act: -0.0001

Data Index: 471989 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.8886. Min Act: -0.0001

Data Index: 525353 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.3955. Min Act: -0.0001

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.7998. Min Act: -0.0001

Data Index: 521279 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.3732. Min Act: -0.0001

Data Index: 2315 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.2183. Min Act: -0.0001

Data Index: 305762 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.2666. Min Act: -0.0001

Data Index: 789766 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.8199. Min Act: -0.0001

Data Index: 661587 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.2884. Min Act: -0.0001

Data Index: 814403 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.6175. Min Act: -0.0001

Data Index: 535196 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.9538. Min Act: -0.0001

Data Index: 1081857 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 4.0077. Min Range: -4.0077

Max Act: 3.2211. Min Act: -0.0001

Data Index: 1172541 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.7976. Min Act: -0.0001

Data Index: 47247 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.4791. Min Act: -0.0001

Data Index: 853604 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.7916. Min Act: -0.0001

Data Index: 135607 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 4.0077. Min Range: -4.0077

Max Act: 2.5892. Min Act: -0.0001

Data Index: 351289 (C4 (Web Text))

Max Activating Token Index: 886