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

Dataset: The Pile

Neuron 1062 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5593. Min Act: -0.0000

Data Index: 603218 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1056029 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1144109 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4633. Min Act: -0.0000

Data Index: 931259 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4627. Min Act: -0.0000

Data Index: 323819 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4145. Min Act: -0.0000

Data Index: 927235 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.4315. Min Act: -0.0000

Data Index: 588332 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3652. Min Act: -0.0000

Data Index: 492269 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3454. Min Act: -0.0000

Data Index: 1915148 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3746. Min Act: -0.0000

Data Index: 59283 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3597. Min Act: -0.0000

Data Index: 485347 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1412174 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3967. Min Act: -0.0000

Data Index: 637240 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3702. Min Act: -0.0000

Data Index: 127139 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1118279 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3334. Min Act: -0.0000

Data Index: 751481 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1842292 (The Pile)

Max Activating Token Index: 157

Text #17

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3474. Min Act: -0.0000

Data Index: 196182 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1237063 (The Pile)

Max Activating Token Index: 934

Text #19

Max Range: 0.5593. Min Range: -0.5593

Max Act: 0.3215. Min Act: -0.0000

Data Index: 982058 (The Pile)

Max Activating Token Index: 442