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

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

Neuron 3174 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1407042 (Python Code)

Max Activating Token Index: 211

Text #1

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1497979 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1636888 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1435672 (Python Code)

Max Activating Token Index: 459

Text #4

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1625796 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1448403 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1578369 (Python Code)

Max Activating Token Index: 548

Text #7

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1426857 (Python Code)

Max Activating Token Index: 418

Text #8

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1461617 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1492020 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1376285 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1406051 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1642983 (Python Code)

Max Activating Token Index: 878

Text #13

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1440578 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1551256 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1601055 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2961. Min Act: -0.0000

Data Index: 1491286 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1430066 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1250983 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.4031. Min Range: -0.4031

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1618205 (Python Code)

Max Activating Token Index: 57