Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 818 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1079950 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1786. Min Act: -0.0000

Data Index: 69534 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1305045 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1645. Min Act: -0.0000

Data Index: 682648 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1537. Min Act: -0.0000

Data Index: 112503 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1592. Min Act: -0.0000

Data Index: 337360 (The Pile)

Max Activating Token Index: 378

Text #6

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1380. Min Act: -0.0000

Data Index: 806811 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1410196 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1311. Min Act: -0.0000

Data Index: 221468 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1137. Min Act: -0.0000

Data Index: 795125 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1334596 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1308. Min Act: -0.0000

Data Index: 831318 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1250. Min Act: -0.0000

Data Index: 756016 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1058763 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1220. Min Act: -0.0000

Data Index: 273473 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1025710 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1190. Min Act: -0.0000

Data Index: 301435 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1213. Min Act: -0.0000

Data Index: 984810 (The Pile)

Max Activating Token Index: 404

Text #18

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1138. Min Act: -0.0000

Data Index: 960048 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 0.3034. Min Range: -0.3034

Max Act: 0.1057. Min Act: -0.0001

Data Index: 663761 (The Pile)

Max Activating Token Index: 784