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

Dataset: The Pile

Neuron 3278 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.6055. Min Act: -0.0000

Data Index: 1377070 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.7585. Min Act: -0.0000

Data Index: 1133928 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.8979. Min Act: -0.0000

Data Index: 93927 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.7336. Min Act: -0.0000

Data Index: 1652799 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.4890. Min Act: -0.0000

Data Index: 1638151 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.6383. Min Act: -0.0000

Data Index: 1580216 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.5742. Min Act: -0.0000

Data Index: 632274 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.6966. Min Act: -0.0000

Data Index: 1554551 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.5295. Min Act: -0.0000

Data Index: 245116 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.4338. Min Act: -0.0000

Data Index: 56076 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.4135. Min Act: -0.0000

Data Index: 854403 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.3929. Min Act: -0.0000

Data Index: 1114782 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.2253. Min Act: -0.0000

Data Index: 499917 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.5192. Min Act: -0.0000

Data Index: 443364 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.2048. Min Act: -0.0000

Data Index: 85152 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.3299. Min Act: -0.0000

Data Index: 644265 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.3113. Min Act: -0.0000

Data Index: 272883 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.1646. Min Act: -0.0000

Data Index: 1425697 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.1452. Min Act: -0.0000

Data Index: 801398 (The Pile)

Max Activating Token Index: 1002

Text #19

Max Range: 3.8979. Min Range: -3.8979

Max Act: 3.1236. Min Act: -0.0000

Data Index: 737320 (The Pile)

Max Activating Token Index: 584