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

Dataset: The Pile

Neuron 610 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: 0.5153. Min Range: -0.5153

Max Act: 0.4940. Min Act: -0.0000

Data Index: 896445 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.5153. Min Act: -0.0000

Data Index: 655687 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4786. Min Act: -0.0000

Data Index: 965338 (The Pile)

Max Activating Token Index: 716

Text #3

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4523. Min Act: -0.0000

Data Index: 967441 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1231418 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4684. Min Act: -0.0000

Data Index: 568825 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1325423 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1560477 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1320213 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4432. Min Act: -0.0000

Data Index: 551974 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4779. Min Act: -0.0000

Data Index: 65030 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4356. Min Act: -0.0000

Data Index: 183438 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1392192 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4443. Min Act: -0.0000

Data Index: 562427 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1833702 (The Pile)

Max Activating Token Index: 226

Text #15

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1516853 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4435. Min Act: -0.0000

Data Index: 158932 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1883930 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4004. Min Act: -0.0000

Data Index: 725918 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.5153. Min Range: -0.5153

Max Act: 0.4100. Min Act: -0.0000

Data Index: 678374 (The Pile)

Max Activating Token Index: 254