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

Dataset: The Pile

Neuron 368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1067927 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.6611. Min Act: -0.0000

Data Index: 1141289 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.5050. Min Act: -0.0000

Data Index: 287243 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.5319. Min Act: -0.0000

Data Index: 922166 (The Pile)

Max Activating Token Index: 288

Text #4

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.2626. Min Act: -0.0000

Data Index: 207982 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1626019 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.0762. Min Act: -0.0000

Data Index: 262518 (The Pile)

Max Activating Token Index: 725

Text #7

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.2034. Min Act: -0.0000

Data Index: 323624 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.2128. Min Act: -0.0000

Data Index: 7146 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1058823 (The Pile)

Max Activating Token Index: 53

Text #10

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.1718. Min Act: -0.0000

Data Index: 984029 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1615669 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.1310. Min Act: -0.0000

Data Index: 993262 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1403490 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.1827. Min Act: -0.0000

Data Index: 341700 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.0021. Min Act: -0.0000

Data Index: 982271 (The Pile)

Max Activating Token Index: 225

Text #16

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.0909. Min Act: -0.0000

Data Index: 612585 (The Pile)

Max Activating Token Index: 140

Text #17

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1104956 (The Pile)

Max Activating Token Index: 353

Text #18

Max Range: 1.6611. Min Range: -1.6611

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1694252 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.6611. Min Range: -1.6611

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1270078 (The Pile)

Max Activating Token Index: 428