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

Dataset: The Pile

Neuron 1467 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: 0.9541. Min Range: -0.9541

Max Act: 0.9541. Min Act: -0.0000

Data Index: 855131 (The Pile)

Max Activating Token Index: 838

Text #1

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1880345 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.8124. Min Act: -0.0000

Data Index: 66701 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1557651 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7671. Min Act: -0.0000

Data Index: 138109 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7172. Min Act: -0.0000

Data Index: 792141 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7542. Min Act: -0.0000

Data Index: 681224 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7305. Min Act: -0.0000

Data Index: 837007 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6765. Min Act: -0.0000

Data Index: 245052 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6871. Min Act: -0.0000

Data Index: 757853 (The Pile)

Max Activating Token Index: 200

Text #10

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6676. Min Act: -0.0000

Data Index: 657573 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.7769. Min Act: -0.0000

Data Index: 959212 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1006486 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6443. Min Act: -0.0000

Data Index: 597442 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6019. Min Act: -0.0000

Data Index: 120668 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6154. Min Act: -0.0000

Data Index: 97035 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1171636 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1848827 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1821759 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.9541. Min Range: -0.9541

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1762508 (The Pile)

Max Activating Token Index: 490