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

Dataset: The Pile

Neuron 804 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1853157 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4963. Min Act: -0.0000

Data Index: 797026 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1639257 (The Pile)

Max Activating Token Index: 989

Text #3

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1760740 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5171. Min Act: -0.0000

Data Index: 347844 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4346. Min Act: -0.0000

Data Index: 998110 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1213527 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1500630 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1005270 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1681406 (The Pile)

Max Activating Token Index: 492

Text #10

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4653. Min Act: -0.0000

Data Index: 330984 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1115921 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4496. Min Act: -0.0000

Data Index: 197225 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4457. Min Act: -0.0000

Data Index: 15124 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4179. Min Act: -0.0000

Data Index: 633997 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4411. Min Act: -0.0000

Data Index: 355609 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1198543 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1835306 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1473308 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.5438. Min Range: -0.5438

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1880170 (The Pile)

Max Activating Token Index: 719