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

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

Neuron 3793 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.7709. Min Act: 0.0000

Data Index: 371293 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.8465. Min Act: -0.0000

Data Index: 810400 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.6721. Min Act: -0.0000

Data Index: 490792 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.6751. Min Act: -0.0000

Data Index: 44679 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.6587. Min Act: -0.0000

Data Index: 419651 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.5874. Min Act: -0.0000

Data Index: 683330 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.4863. Min Act: -0.0000

Data Index: 801831 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.4938. Min Act: -0.0000

Data Index: 664265 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.4383. Min Act: -0.0000

Data Index: 950413 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.4123. Min Act: -0.0000

Data Index: 16708 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1269662 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3287. Min Act: -0.0000

Data Index: 913442 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3217. Min Act: -0.0000

Data Index: 271148 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3553. Min Act: -0.0000

Data Index: 813693 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3326. Min Act: -0.0000

Data Index: 548612 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3287. Min Act: -0.0000

Data Index: 117735 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.2800. Min Act: -0.0000

Data Index: 770433 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.2211. Min Act: -0.0000

Data Index: 40487 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.2634. Min Act: -0.0000

Data Index: 1074327 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 1.8465. Min Range: -1.8465

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1474039 (Python Code)

Max Activating Token Index: 931