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

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

Neuron 449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0236. Min Range: -4.0236

Max Act: 4.0236. Min Act: -0.0000

Data Index: 454963 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.9936. Min Act: -0.0000

Data Index: 1379165 (Python Code)

Max Activating Token Index: 405

Text #2

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.1153. Min Act: -0.0000

Data Index: 1387486 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8822. Min Act: -0.0000

Data Index: 1645556 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.9725. Min Act: -0.0000

Data Index: 1515019 (Python Code)

Max Activating Token Index: 892

Text #5

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8347. Min Act: -0.0000

Data Index: 1652044 (Python Code)

Max Activating Token Index: 988

Text #6

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.6785. Min Act: -0.0000

Data Index: 1543835 (Python Code)

Max Activating Token Index: 866

Text #7

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.0640. Min Act: -0.0000

Data Index: 193542 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1181748 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8575. Min Act: -0.0000

Data Index: 145 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.0332. Min Act: -0.0000

Data Index: 1513720 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8748. Min Act: -0.0000

Data Index: 273732 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8797. Min Act: -0.0000

Data Index: 1516949 (Python Code)

Max Activating Token Index: 332

Text #13

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.0020. Min Act: -0.0000

Data Index: 895179 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.5851. Min Act: -0.0000

Data Index: 793182 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8693. Min Act: -0.0000

Data Index: 1566104 (Python Code)

Max Activating Token Index: 310

Text #16

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.1424. Min Act: -0.0000

Data Index: 1499229 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 4.0236. Min Range: -4.0236

Max Act: 3.1008. Min Act: -0.0000

Data Index: 888982 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8118. Min Act: -0.0000

Data Index: 1099675 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 4.0236. Min Range: -4.0236

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1377299 (Python Code)

Max Activating Token Index: 905