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

Dataset: The Pile

Neuron 3117 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: 0.6043. Min Range: -0.6043

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1991449 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.6043. Min Act: -0.0000

Data Index: 837967 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.5272. Min Act: -0.0000

Data Index: 711610 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1686241 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.3844. Min Act: -0.0000

Data Index: 237567 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4773. Min Act: -0.0000

Data Index: 258145 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4854. Min Act: -0.0000

Data Index: 8363 (The Pile)

Max Activating Token Index: 479

Text #7

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4495. Min Act: -0.0000

Data Index: 586384 (The Pile)

Max Activating Token Index: 502

Text #8

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4965. Min Act: -0.0000

Data Index: 497431 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1060731 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4315. Min Act: -0.0000

Data Index: 1500994 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4108. Min Act: -0.0000

Data Index: 456390 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4672. Min Act: -0.0000

Data Index: 908626 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1558876 (The Pile)

Max Activating Token Index: 85

Text #14

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4551. Min Act: -0.0000

Data Index: 290607 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4586. Min Act: -0.0000

Data Index: 281160 (The Pile)

Max Activating Token Index: 367

Text #16

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4194. Min Act: -0.0000

Data Index: 381242 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1536982 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1276864 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 0.6043. Min Range: -0.6043

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1432753 (The Pile)

Max Activating Token Index: 763