Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3328 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.0224. Min Range: -5.0224

Max Act: 5.0224. Min Act: -0.0000

Data Index: 1995542 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.6339. Min Act: -0.0000

Data Index: 1295143 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.7408. Min Act: -0.0000

Data Index: 1147371 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.2845. Min Act: -0.0000

Data Index: 1131205 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.3519. Min Act: -0.0000

Data Index: 913518 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.9434. Min Act: -0.0000

Data Index: 1672786 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.2831. Min Act: -0.0000

Data Index: 1951487 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.2729. Min Act: -0.0000

Data Index: 543242 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.0393. Min Act: -0.0000

Data Index: 153845 (The Pile)

Max Activating Token Index: 76

Text #9

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.2223. Min Act: -0.0000

Data Index: 1517732 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 5.0224. Min Range: -5.0224

Max Act: 4.0606. Min Act: -0.0000

Data Index: 1978017 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.7227. Min Act: -0.0000

Data Index: 1114285 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.8620. Min Act: -0.0000

Data Index: 800291 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.7780. Min Act: -0.0000

Data Index: 1593146 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.7513. Min Act: -0.0000

Data Index: 1211611 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.8687. Min Act: -0.0000

Data Index: 27448 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.6777. Min Act: -0.0000

Data Index: 642560 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.6535. Min Act: -0.0000

Data Index: 616319 (The Pile)

Max Activating Token Index: 559

Text #18

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.6162. Min Act: -0.0000

Data Index: 322600 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 5.0224. Min Range: -5.0224

Max Act: 3.7610. Min Act: -0.0000

Data Index: 1712339 (The Pile)

Max Activating Token Index: 41