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

Dataset: The Pile

Neuron 2231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4299. Min Act: -0.0000

Data Index: 230951 (The Pile)

Max Activating Token Index: 249

Text #1

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4451. Min Act: -0.0000

Data Index: 814262 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1557665 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1642284 (The Pile)

Max Activating Token Index: 991

Text #4

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4358. Min Act: -0.0000

Data Index: 988368 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1075451 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4049. Min Act: -0.0000

Data Index: 781013 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1008705 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3876. Min Act: -0.0000

Data Index: 359264 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3385. Min Act: -0.0000

Data Index: 89578 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1185600 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3662. Min Act: -0.0000

Data Index: 545580 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3791. Min Act: -0.0000

Data Index: 826133 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3568. Min Act: -0.0000

Data Index: 888075 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3411. Min Act: -0.0000

Data Index: 975627 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1833301 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1147259 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3460. Min Act: -0.0000

Data Index: 1296123 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3636. Min Act: -0.0000

Data Index: 219013 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1859220 (The Pile)

Max Activating Token Index: 418