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

Dataset: The Pile

Neuron 1079 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: 0.4400. Min Range: -0.4400

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1664043 (The Pile)

Max Activating Token Index: 870

Text #1

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1070150 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1839310 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3424. Min Act: -0.0000

Data Index: 265652 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1767124 (The Pile)

Max Activating Token Index: 753

Text #5

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3350. Min Act: -0.0000

Data Index: 156547 (The Pile)

Max Activating Token Index: 349

Text #6

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1932845 (The Pile)

Max Activating Token Index: 351

Text #7

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3237. Min Act: -0.0000

Data Index: 251398 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3085. Min Act: -0.0000

Data Index: 547309 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2938. Min Act: -0.0000

Data Index: 595618 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1821197 (The Pile)

Max Activating Token Index: 625

Text #11

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.3157. Min Act: -0.0000

Data Index: 757505 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2940. Min Act: -0.0000

Data Index: 880218 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2955. Min Act: -0.0000

Data Index: 396882 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1405810 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2818. Min Act: -0.0000

Data Index: 574817 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2745. Min Act: -0.0000

Data Index: 772022 (The Pile)

Max Activating Token Index: 771

Text #17

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1160019 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1138679 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.4400. Min Range: -0.4400

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1329217 (The Pile)

Max Activating Token Index: 861