Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3205 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 332918 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4008. Min Act: -0.0000

Data Index: 754623 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1830154 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3571. Min Act: -0.0000

Data Index: 360711 (The Pile)

Max Activating Token Index: 860

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3682. Min Act: -0.0000

Data Index: 941463 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1608153 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1524695 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3305. Min Act: -0.0000

Data Index: 391741 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2914. Min Act: -0.0000

Data Index: 352220 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3275. Min Act: -0.0000

Data Index: 765925 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3253. Min Act: -0.0000

Data Index: 691049 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3057. Min Act: -0.0000

Data Index: 47199 (The Pile)

Max Activating Token Index: 420

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2971. Min Act: -0.0000

Data Index: 926420 (The Pile)

Max Activating Token Index: 1017

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1927689 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3235. Min Act: -0.0000

Data Index: 1631329 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1805282 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1583574 (The Pile)

Max Activating Token Index: 797

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1037987 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3139. Min Act: -0.0000

Data Index: 94828 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1660665 (The Pile)

Max Activating Token Index: 729