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

Dataset: The Pile

Neuron 4056 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0222. Min Range: -1.0222

Max Act: 1.0222. Min Act: -0.0000

Data Index: 250618 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.9210. Min Act: -0.0000

Data Index: 716530 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1452759 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1182436 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1544602 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1055123 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7170. Min Act: -0.0000

Data Index: 532654 (The Pile)

Max Activating Token Index: 262

Text #7

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1559203 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1741018 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1424491 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1111890 (The Pile)

Max Activating Token Index: 66

Text #11

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1247521 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6734. Min Act: -0.0000

Data Index: 11865 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1605548 (The Pile)

Max Activating Token Index: 81

Text #14

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1345286 (The Pile)

Max Activating Token Index: 771

Text #15

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1881554 (The Pile)

Max Activating Token Index: 359

Text #16

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1192363 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6409. Min Act: -0.0000

Data Index: 40095 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1355868 (The Pile)

Max Activating Token Index: 263

Text #19

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.6164. Min Act: -0.0000

Data Index: 513301 (The Pile)

Max Activating Token Index: 585