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

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

Neuron 2200 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5718. Min Act: -0.0000

Data Index: 191699 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1246414 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.5135. Min Act: -0.0000

Data Index: 641987 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4277. Min Act: -0.0000

Data Index: 802250 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1353950 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4787. Min Act: -0.0000

Data Index: 382364 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4418. Min Act: -0.0000

Data Index: 954777 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4740. Min Act: -0.0000

Data Index: 145474 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1135928 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4345. Min Act: -0.0000

Data Index: 742252 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4319. Min Act: -0.0000

Data Index: 70279 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4463. Min Act: -0.0000

Data Index: 1045153 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1205852 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3145. Min Act: -0.0000

Data Index: 518035 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.4196. Min Act: -0.0000

Data Index: 73716 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3912. Min Act: -0.0000

Data Index: 967409 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3945. Min Act: -0.0000

Data Index: 687439 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1634361 (Python Code)

Max Activating Token Index: 29

Text #18

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3830. Min Act: -0.0000

Data Index: 484927 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.5718. Min Range: -0.5718

Max Act: 0.3663. Min Act: -0.0000

Data Index: 524162 (C4 (Web Text))

Max Activating Token Index: 1010