Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6109 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.5070. Min Act: -0.0000

Data Index: 1325497 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.3625. Min Act: -0.0000

Data Index: 635439 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.3320. Min Act: -0.0000

Data Index: 1122691 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.1195. Min Act: -0.0000

Data Index: 1014693 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 2.5070. Min Range: -2.5070

Max Act: 2.0081. Min Act: -0.0000

Data Index: 45215 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.9101. Min Act: -0.0000

Data Index: 952565 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.7660. Min Act: -0.0000

Data Index: 1078894 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.8299. Min Act: -0.0000

Data Index: 93406 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.8758. Min Act: -0.0000

Data Index: 799083 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.7553. Min Act: -0.0000

Data Index: 418106 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6536. Min Act: -0.0000

Data Index: 81948 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.7378. Min Act: -0.0000

Data Index: 1126073 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1051275 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6975. Min Act: -0.0000

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6425. Min Act: -0.0000

Data Index: 178281 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6598. Min Act: -0.0000

Data Index: 370874 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.5598. Min Act: -0.0000

Data Index: 647652 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6541. Min Act: -0.0000

Data Index: 1213657 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.5496. Min Act: -0.0000

Data Index: 143621 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 2.5070. Min Range: -2.5070

Max Act: 1.6235. Min Act: -0.0000

Data Index: 489133 (C4 (Web Text))

Max Activating Token Index: 590