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

Dataset: The Pile

Neuron 3975 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1255583 (The Pile)

Max Activating Token Index: 212

Text #1

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.4106. Min Act: -0.0000

Data Index: 621484 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3338. Min Act: -0.0000

Data Index: 302817 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1427885 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1071322 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1163013 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3340. Min Act: -0.0000

Data Index: 301540 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3153. Min Act: -0.0000

Data Index: 636267 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3138. Min Act: -0.0000

Data Index: 519330 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2885. Min Act: -0.0000

Data Index: 591147 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3059. Min Act: -0.0000

Data Index: 407290 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1197389 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1401099 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3029. Min Act: -0.0000

Data Index: 554811 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3014. Min Act: -0.0000

Data Index: 644009 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1175328 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3237. Min Act: -0.0000

Data Index: 811436 (The Pile)

Max Activating Token Index: 578

Text #17

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2969. Min Act: -0.0000

Data Index: 982262 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1990142 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2788. Min Act: -0.0000

Data Index: 665069 (The Pile)

Max Activating Token Index: 467