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

Dataset: The Pile

Neuron 2201 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: 1.7115. Min Range: -1.7115

Max Act: 1.5311. Min Act: -0.0000

Data Index: 556837 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.6467. Min Act: -0.0000

Data Index: 863100 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5942. Min Act: -0.0000

Data Index: 57872 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4608. Min Act: -0.0000

Data Index: 1452016 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.3151. Min Act: -0.0000

Data Index: 1264268 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1443148 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4726. Min Act: -0.0000

Data Index: 103454 (The Pile)

Max Activating Token Index: 347

Text #7

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1782502 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4483. Min Act: -0.0000

Data Index: 1418815 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.7115. Min Act: -0.0000

Data Index: 108608 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4979. Min Act: -0.0000

Data Index: 1206312 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4668. Min Act: -0.0000

Data Index: 236075 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1447261 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5690. Min Act: -0.0000

Data Index: 440551 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1583390 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.3118. Min Act: -0.0000

Data Index: 665074 (The Pile)

Max Activating Token Index: 924

Text #16

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.5885. Min Act: -0.0000

Data Index: 1885656 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.3633. Min Act: -0.0000

Data Index: 993072 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.6120. Min Act: -0.0000

Data Index: 908189 (The Pile)

Max Activating Token Index: 912

Text #19

Max Range: 1.7115. Min Range: -1.7115

Max Act: 1.4914. Min Act: -0.0000

Data Index: 365387 (The Pile)

Max Activating Token Index: 404