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

Dataset: The Pile

Neuron 3182 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5803. Min Act: -0.0000

Data Index: 648735 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1953852 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1570689 (The Pile)

Max Activating Token Index: 21

Text #3

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1472621 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5834. Min Act: -0.0000

Data Index: 60336 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5455. Min Act: -0.0000

Data Index: 1510214 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1262161 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4957. Min Act: -0.0000

Data Index: 618994 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1013876 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1718316 (The Pile)

Max Activating Token Index: 692

Text #10

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1428656 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1882953 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1236080 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4524. Min Act: -0.0000

Data Index: 41872 (The Pile)

Max Activating Token Index: 405

Text #14

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4628. Min Act: -0.0000

Data Index: 230468 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4789. Min Act: -0.0000

Data Index: 52070 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4224. Min Act: -0.0000

Data Index: 725313 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4455. Min Act: -0.0000

Data Index: 358890 (The Pile)

Max Activating Token Index: 429

Text #18

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1343060 (The Pile)

Max Activating Token Index: 152

Text #19

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4857. Min Act: -0.0000

Data Index: 179444 (The Pile)

Max Activating Token Index: 613