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

Dataset: The Pile

Neuron 770 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3681. Min Act: -0.0000

Data Index: 976094 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1402528 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1673321 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1773857 (The Pile)

Max Activating Token Index: 207

Text #4

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3280. Min Act: -0.0000

Data Index: 1909706 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1106805 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1513431 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1546596 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1370742 (The Pile)

Max Activating Token Index: 632

Text #9

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3137. Min Act: -0.0000

Data Index: 919988 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2865. Min Act: -0.0000

Data Index: 639304 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3010. Min Act: -0.0000

Data Index: 253722 (The Pile)

Max Activating Token Index: 136

Text #12

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1146350 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2875. Min Act: -0.0000

Data Index: 772976 (The Pile)

Max Activating Token Index: 864

Text #14

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1526029 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1718196 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2973. Min Act: -0.0000

Data Index: 967659 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1571473 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2963. Min Act: -0.0000

Data Index: 406463 (The Pile)

Max Activating Token Index: 302

Text #19

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3104. Min Act: -0.0000

Data Index: 913235 (The Pile)

Max Activating Token Index: 1010