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

Dataset: The Pile

Neuron 767 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1230539 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3928. Min Act: -0.0000

Data Index: 62692 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3644. Min Act: -0.0000

Data Index: 899373 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3880. Min Act: -0.0000

Data Index: 233947 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3953. Min Act: -0.0000

Data Index: 505492 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1512806 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1514900 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1782831 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1599000 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3322. Min Act: -0.0000

Data Index: 7578 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1205122 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3278. Min Act: -0.0000

Data Index: 967197 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1157898 (The Pile)

Max Activating Token Index: 953

Text #13

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1907407 (The Pile)

Max Activating Token Index: 509

Text #14

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3195. Min Act: -0.0000

Data Index: 508795 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1499047 (The Pile)

Max Activating Token Index: 52

Text #16

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1220167 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1338287 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.3441. Min Act: -0.0000

Data Index: 1979061 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.3953. Min Range: -0.3953

Max Act: 0.2874. Min Act: -0.0000

Data Index: 725918 (The Pile)

Max Activating Token Index: 791