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

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

Neuron 3041 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: 0.3113. Min Range: -0.3113

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1163343 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2740. Min Act: -0.0000

Data Index: 165781 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2808. Min Act: -0.0000

Data Index: 986592 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2655. Min Act: -0.0000

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2633. Min Act: -0.0000

Data Index: 337626 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1463633 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1146894 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2603. Min Act: -0.0000

Data Index: 615737 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2528. Min Act: -0.0000

Data Index: 587444 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1290910 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2675. Min Act: -0.0000

Data Index: 140439 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1511244 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1075972 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1162856 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1583509 (Python Code)

Max Activating Token Index: 586

Text #16

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2296. Min Act: -0.0000

Data Index: 459339 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2280. Min Act: -0.0000

Data Index: 212578 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1517209 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2161. Min Act: -0.0000

Data Index: 907097 (C4 (Web Text))

Max Activating Token Index: 357