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

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

Neuron 4728 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.6019. Min Act: -0.0000

Data Index: 313744 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5995. Min Act: -0.0000

Data Index: 130499 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.5862. Min Act: -0.0000

Data Index: 769320 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1041895 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1040647 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4844. Min Act: -0.0000

Data Index: 183309 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4777. Min Act: -0.0000

Data Index: 181 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4740. Min Act: -0.0000

Data Index: 598246 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4857. Min Act: -0.0000

Data Index: 652997 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4560. Min Act: -0.0000

Data Index: 898033 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4886. Min Act: -0.0000

Data Index: 790221 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4515. Min Act: -0.0000

Data Index: 343007 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.3898. Min Act: -0.0000

Data Index: 242300 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4643. Min Act: -0.0000

Data Index: 344628 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4431. Min Act: -0.0000

Data Index: 594723 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4405. Min Act: -0.0000

Data Index: 234448 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4550. Min Act: -0.0000

Data Index: 672694 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4779. Min Act: -0.0000

Data Index: 529510 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4707. Min Act: -0.0000

Data Index: 116520 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.6019. Min Range: -0.6019

Max Act: 0.4211. Min Act: -0.0000

Data Index: 178408 (C4 (Web Text))

Max Activating Token Index: 34