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

Dataset: The Pile

Neuron 1810 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5986. Min Act: -0.0000

Data Index: 914882 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5366. Min Act: -0.0000

Data Index: 1602114 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.5333. Min Act: -0.0000

Data Index: 457676 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4159. Min Act: -0.0000

Data Index: 846507 (The Pile)

Max Activating Token Index: 71

Text #4

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3438. Min Act: -0.0000

Data Index: 323642 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4305. Min Act: -0.0000

Data Index: 1135726 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3746. Min Act: -0.0000

Data Index: 1476336 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.4533. Min Act: -0.0000

Data Index: 1537649 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1906327 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1159033 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2972. Min Act: -0.0000

Data Index: 849035 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3105. Min Act: -0.0000

Data Index: 350226 (The Pile)

Max Activating Token Index: 404

Text #12

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2972. Min Act: -0.0000

Data Index: 1234315 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1160835 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1996956 (The Pile)

Max Activating Token Index: 684

Text #15

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1780816 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1114522 (The Pile)

Max Activating Token Index: 694

Text #17

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1009677 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2084. Min Act: -0.0000

Data Index: 642132 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.5986. Min Range: -1.5986

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1253228 (The Pile)

Max Activating Token Index: 536