Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4136 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1229679 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1152853 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3196. Min Act: -0.0000

Data Index: 614439 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3364. Min Act: -0.0000

Data Index: 487144 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3191. Min Act: -0.0000

Data Index: 204396 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1166562 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3038. Min Act: -0.0000

Data Index: 804673 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1127768 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2880. Min Act: -0.0000

Data Index: 552438 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2861. Min Act: -0.0000

Data Index: 108815 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2740. Min Act: -0.0000

Data Index: 929009 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2649. Min Act: -0.0000

Data Index: 501398 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2714. Min Act: -0.0000

Data Index: 310808 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2712. Min Act: -0.0000

Data Index: 330050 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2716. Min Act: -0.0000

Data Index: 535354 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2660. Min Act: -0.0000

Data Index: 192964 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1276277 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2644. Min Act: -0.0000

Data Index: 332424 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1028682 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2535. Min Act: -0.0000

Data Index: 558041 (C4 (Web Text))

Max Activating Token Index: 650