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

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

Neuron 1708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0497. Min Act: -0.0000

Data Index: 515410 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0427. Min Act: -0.0000

Data Index: 546354 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0426. Min Act: -0.0000

Data Index: 87545 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0404. Min Act: -0.0001

Data Index: 628106 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0356. Min Act: -0.0000

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0000

Data Index: 14863 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0345. Min Act: -0.0000

Data Index: 518419 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1294177 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0364. Min Act: -0.0001

Data Index: 1278622 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0364. Min Act: -0.0000

Data Index: 34568 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1338213 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1163189 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0371. Min Act: -0.0000

Data Index: 117758 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1337664 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0322. Min Act: -0.0000

Data Index: 836325 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0345. Min Act: -0.0000

Data Index: 751333 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0337. Min Act: -0.0001

Data Index: 37294 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0347. Min Act: -0.0000

Data Index: 564951 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0362. Min Act: -0.0001

Data Index: 856701 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0295. Min Act: -0.0000

Data Index: 31812 (C4 (Web Text))

Max Activating Token Index: 80