Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5445 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.6203. Min Act: -0.0001

Data Index: 1083650 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5728. Min Act: -0.0001

Data Index: 6733 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1317806 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1364805 (Python Code)

Max Activating Token Index: 855

Text #4

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5462. Min Act: -0.0001

Data Index: 433014 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5047. Min Act: -0.0001

Data Index: 514202 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5146. Min Act: -0.0001

Data Index: 456082 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.5190. Min Act: -0.0001

Data Index: 540136 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4685. Min Act: -0.0001

Data Index: 1272252 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1182427 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1098248 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4288. Min Act: -0.0001

Data Index: 1453992 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4754. Min Act: -0.0001

Data Index: 1325522 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4468. Min Act: -0.0001

Data Index: 555523 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4864. Min Act: -0.0001

Data Index: 298441 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4486. Min Act: -0.0001

Data Index: 314908 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1599534 (Python Code)

Max Activating Token Index: 868

Text #17

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4496. Min Act: -0.0001

Data Index: 1649473 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1657059 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.6203. Min Range: -0.6203

Max Act: 0.4293. Min Act: -0.0001

Data Index: 1248037 (C4 (Web Text))

Max Activating Token Index: 440