Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.7954. Min Act: -0.0001

Data Index: 1386596 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4867. Min Act: -0.0001

Data Index: 1539693 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4482. Min Act: -0.0001

Data Index: 1392507 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2349. Min Act: -0.0001

Data Index: 1564670 (Python Code)

Max Activating Token Index: 749

Text #4

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0694. Min Act: -0.0001

Data Index: 1597715 (Python Code)

Max Activating Token Index: 306

Text #5

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9159. Min Act: -0.0001

Data Index: 1579625 (Python Code)

Max Activating Token Index: 796

Text #6

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2441. Min Act: -0.0001

Data Index: 1420677 (Python Code)

Max Activating Token Index: 793

Text #7

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2529. Min Act: -0.0001

Data Index: 1448631 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0702. Min Act: -0.0001

Data Index: 1607921 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2066. Min Act: -0.0001

Data Index: 1495748 (Python Code)

Max Activating Token Index: 32

Text #10

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.3475. Min Act: -0.0001

Data Index: 1463084 (Python Code)

Max Activating Token Index: 464

Text #11

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.1188. Min Act: -0.0001

Data Index: 1578102 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9772. Min Act: -0.0001

Data Index: 1518234 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0965. Min Act: -0.0001

Data Index: 1551897 (Python Code)

Max Activating Token Index: 774

Text #14

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0942. Min Act: -0.0001

Data Index: 1438024 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0933. Min Act: -0.0001

Data Index: 1558177 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9471. Min Act: -0.0001

Data Index: 1650847 (Python Code)

Max Activating Token Index: 689

Text #17

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.2110. Min Act: -0.0001

Data Index: 1586418 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 3.7954. Min Range: -3.7954

Max Act: 2.9199. Min Act: -0.0001

Data Index: 1400027 (Python Code)

Max Activating Token Index: 399

Text #19

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.0499. Min Act: -0.0001

Data Index: 1441712 (Python Code)

Max Activating Token Index: 947