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

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

Neuron 3907 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4264. Min Act: -0.0001

Data Index: 818478 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4065. Min Act: -0.0001

Data Index: 802642 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4123. Min Act: -0.0001

Data Index: 621587 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4241. Min Act: -0.0000

Data Index: 591367 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4020. Min Act: -0.0001

Data Index: 436858 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4016. Min Act: -0.0001

Data Index: 654137 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3989. Min Act: -0.0001

Data Index: 132653 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4106. Min Act: -0.0000

Data Index: 603336 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4058. Min Act: -0.0000

Data Index: 973396 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3969. Min Act: -0.0001

Data Index: 547944 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.4010. Min Act: -0.0001

Data Index: 910468 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3852. Min Act: -0.0001

Data Index: 181237 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3728. Min Act: -0.0001

Data Index: 461816 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3685. Min Act: -0.0001

Data Index: 45454 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3776. Min Act: -0.0001

Data Index: 918101 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3663. Min Act: -0.0001

Data Index: 760932 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3409. Min Act: -0.0001

Data Index: 411525 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3449. Min Act: -0.0001

Data Index: 677888 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3406. Min Act: -0.0001

Data Index: 673233 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.4264. Min Range: -0.4264

Max Act: 0.3528. Min Act: -0.0001

Data Index: 308383 (C4 (Web Text))

Max Activating Token Index: 73