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

Dataset: The Pile

Neuron 3688 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: 0.4818. Min Range: -0.4818

Max Act: 0.4808. Min Act: -0.0000

Data Index: 808904 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1972219 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4636. Min Act: -0.0000

Data Index: 657415 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4731. Min Act: -0.0000

Data Index: 136274 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1193925 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1824826 (The Pile)

Max Activating Token Index: 245

Text #6

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4818. Min Act: -0.0000

Data Index: 264114 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4444. Min Act: -0.0000

Data Index: 101142 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4421. Min Act: -0.0000

Data Index: 387449 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4210. Min Act: -0.0000

Data Index: 485579 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1084781 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3379. Min Act: -0.0000

Data Index: 322375 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4215. Min Act: -0.0000

Data Index: 878892 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4096. Min Act: -0.0000

Data Index: 397958 (The Pile)

Max Activating Token Index: 511

Text #14

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1443410 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1596045 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3798. Min Act: -0.0000

Data Index: 475071 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3947. Min Act: -0.0000

Data Index: 418149 (The Pile)

Max Activating Token Index: 250

Text #18

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1060302 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1735360 (The Pile)

Max Activating Token Index: 247