Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2186 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.6424. Min Act: -0.0000

Data Index: 1640292 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.5574. Min Act: -0.0000

Data Index: 294347 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1782418 (The Pile)

Max Activating Token Index: 412

Text #3

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.5422. Min Act: -0.0000

Data Index: 654985 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1729198 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1906603 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4958. Min Act: -0.0000

Data Index: 607789 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.5515. Min Act: -0.0000

Data Index: 526240 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4868. Min Act: -0.0000

Data Index: 403312 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4796. Min Act: -0.0001

Data Index: 1842768 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4731. Min Act: -0.0000

Data Index: 826864 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4878. Min Act: -0.0000

Data Index: 99745 (The Pile)

Max Activating Token Index: 905

Text #12

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4851. Min Act: -0.0000

Data Index: 1270967 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4211. Min Act: -0.0001

Data Index: 862760 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4402. Min Act: -0.0000

Data Index: 385705 (The Pile)

Max Activating Token Index: 511

Text #15

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4695. Min Act: -0.0001

Data Index: 1191629 (The Pile)

Max Activating Token Index: 417

Text #16

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4470. Min Act: -0.0000

Data Index: 177201 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4317. Min Act: -0.0001

Data Index: 571873 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1877026 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.6424. Min Range: -0.6424

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1550148 (The Pile)

Max Activating Token Index: 1013