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

Dataset: The Pile

Neuron 1461 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: 0.3959. Min Range: -0.3959

Max Act: 0.3687. Min Act: -0.0000

Data Index: 463457 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1228045 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1907590 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3565. Min Act: -0.0000

Data Index: 173153 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1784082 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3529. Min Act: -0.0000

Data Index: 616914 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1594880 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3349. Min Act: -0.0000

Data Index: 453389 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1831766 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1713321 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3425. Min Act: -0.0000

Data Index: 407723 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1280177 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1475333 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1702330 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3186. Min Act: -0.0000

Data Index: 856027 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1488813 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3083. Min Act: -0.0000

Data Index: 804148 (The Pile)

Max Activating Token Index: 16

Text #17

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1905433 (The Pile)

Max Activating Token Index: 951

Text #18

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1357914 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3080. Min Act: -0.0000

Data Index: 123573 (The Pile)

Max Activating Token Index: 381