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

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

Neuron 2887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.7053. Min Act: -0.0000

Data Index: 1081388 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.5125. Min Act: -0.0000

Data Index: 687147 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.1537. Min Act: -0.0000

Data Index: 1272765 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.1397. Min Act: -0.0000

Data Index: 1449807 (Python Code)

Max Activating Token Index: 433

Text #4

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1245669 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 2.7053. Min Range: -2.7053

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1096519 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8883. Min Act: -0.0000

Data Index: 59933 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.9239. Min Act: -0.0000

Data Index: 838141 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7580. Min Act: -0.0000

Data Index: 899369 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.8184. Min Act: -0.0000

Data Index: 135446 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7046. Min Act: -0.0000

Data Index: 1122628 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7854. Min Act: -0.0000

Data Index: 630584 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1007825 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6962. Min Act: -0.0000

Data Index: 1127639 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6885. Min Act: -0.0000

Data Index: 730034 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.5774. Min Act: -0.0000

Data Index: 1275120 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6554. Min Act: -0.0000

Data Index: 108096 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6176. Min Act: -0.0000

Data Index: 1647273 (Python Code)

Max Activating Token Index: 598

Text #18

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6384. Min Act: -0.0000

Data Index: 132746 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.7053. Min Range: -2.7053

Max Act: 1.6415. Min Act: -0.0000

Data Index: 976015 (C4 (Web Text))

Max Activating Token Index: 480