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

Dataset: The Pile

Neuron 509 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: 0.6761. Min Range: -0.6761

Max Act: 0.6761. Min Act: -0.0000

Data Index: 863811 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1449748 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5188. Min Act: -0.0000

Data Index: 472055 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6282. Min Act: -0.0000

Data Index: 863036 (The Pile)

Max Activating Token Index: 352

Text #4

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4817. Min Act: -0.0000

Data Index: 139942 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5359. Min Act: -0.0000

Data Index: 805643 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1309879 (The Pile)

Max Activating Token Index: 553

Text #7

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4858. Min Act: -0.0000

Data Index: 72187 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5568. Min Act: -0.0000

Data Index: 387743 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1250438 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1416109 (The Pile)

Max Activating Token Index: 750

Text #11

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4951. Min Act: -0.0000

Data Index: 560837 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4913. Min Act: -0.0000

Data Index: 701076 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1914523 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1382680 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4450. Min Act: -0.0000

Data Index: 188511 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1269323 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4448. Min Act: -0.0000

Data Index: 617700 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4579. Min Act: -0.0000

Data Index: 220893 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1647439 (The Pile)

Max Activating Token Index: 635