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

Dataset: The Pile

Neuron 2768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1811561 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.5689. Min Act: -0.0000

Data Index: 170811 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1544613 (The Pile)

Max Activating Token Index: 289

Text #3

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1505885 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4418. Min Act: -0.0000

Data Index: 448162 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1683715 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4461. Min Act: -0.0000

Data Index: 546047 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1406774 (The Pile)

Max Activating Token Index: 563

Text #8

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4270. Min Act: -0.0000

Data Index: 404893 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1062697 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1565443 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1928051 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1011799 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1089244 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4159. Min Act: -0.0000

Data Index: 96616 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4182. Min Act: -0.0000

Data Index: 496684 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4009. Min Act: -0.0000

Data Index: 463549 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4427. Min Act: -0.0000

Data Index: 451786 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1060483 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.7456. Min Range: -0.7456

Max Act: 0.3934. Min Act: -0.0000

Data Index: 552689 (The Pile)

Max Activating Token Index: 276