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

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

Neuron 4063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.4677. Min Act: -0.0001

Data Index: 255062 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.0520. Min Act: -0.0001

Data Index: 1092237 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.0129. Min Act: -0.0001

Data Index: 1331429 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 1.4677. Min Range: -1.4677

Max Act: 1.0397. Min Act: -0.0001

Data Index: 570020 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.9511. Min Act: -0.0001

Data Index: 1147384 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.9375. Min Act: -0.0001

Data Index: 855198 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8985. Min Act: -0.0001

Data Index: 531716 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.9325. Min Act: -0.0001

Data Index: 116629 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8971. Min Act: -0.0001

Data Index: 90063 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8740. Min Act: -0.0001

Data Index: 320194 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8991. Min Act: -0.0001

Data Index: 631306 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8987. Min Act: -0.0001

Data Index: 1249817 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8459. Min Act: -0.0001

Data Index: 506723 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8458. Min Act: -0.0001

Data Index: 1318897 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8450. Min Act: -0.0001

Data Index: 1247238 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8465. Min Act: -0.0001

Data Index: 139623 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8355. Min Act: -0.0001

Data Index: 175882 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8128. Min Act: -0.0001

Data Index: 236107 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8344. Min Act: -0.0001

Data Index: 1339684 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.4677. Min Range: -1.4677

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1073318 (C4 (Web Text))

Max Activating Token Index: 971