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

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

Neuron 1723 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.5401. Min Act: -0.0001

Data Index: 475391 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.6343. Min Act: -0.0001

Data Index: 610930 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.5718. Min Act: -0.0001

Data Index: 1287388 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.4685. Min Act: -0.0001

Data Index: 945464 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.4231. Min Act: -0.0001

Data Index: 1301321 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.3528. Min Act: -0.0001

Data Index: 192699 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.2991. Min Act: -0.0001

Data Index: 271288 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.3291. Min Act: -0.0001

Data Index: 507600 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.3774. Min Act: -0.0001

Data Index: 282838 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.3388. Min Act: -0.0001

Data Index: 1276185 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.2019. Min Act: -0.0001

Data Index: 369954 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.3299. Min Act: -0.0001

Data Index: 663028 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1696. Min Act: -0.0001

Data Index: 918056 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1344. Min Act: -0.0000

Data Index: 408407 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1705. Min Act: -0.0001

Data Index: 402399 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1175. Min Act: -0.0001

Data Index: 1340323 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.2584. Min Act: -0.0001

Data Index: 1291628 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1986. Min Act: -0.0000

Data Index: 431754 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.6343. Min Range: -1.6343

Max Act: 0.9847. Min Act: -0.0001

Data Index: 659321 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.6343. Min Range: -1.6343

Max Act: 1.1689. Min Act: -0.0001

Data Index: 794987 (C4 (Web Text))

Max Activating Token Index: 729