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

Dataset: The Pile

Neuron 633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1215453 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1275186 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5001. Min Act: -0.0000

Data Index: 183752 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1769284 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4939. Min Act: -0.0000

Data Index: 439863 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1125742 (The Pile)

Max Activating Token Index: 38

Text #6

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.5065. Min Act: -0.0000

Data Index: 254416 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1147144 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4709. Min Act: -0.0000

Data Index: 464873 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4575. Min Act: -0.0000

Data Index: 442915 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4471. Min Act: -0.0000

Data Index: 63327 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1259711 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4438. Min Act: -0.0000

Data Index: 781519 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1784753 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1445635 (The Pile)

Max Activating Token Index: 262

Text #15

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1315212 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4457. Min Act: -0.0000

Data Index: 685200 (The Pile)

Max Activating Token Index: 68

Text #17

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1805644 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1366125 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 0.5227. Min Range: -0.5227

Max Act: 0.4221. Min Act: -0.0000

Data Index: 450932 (The Pile)

Max Activating Token Index: 315