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

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

Neuron 1554 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.7804. Min Act: -0.0000

Data Index: 627361 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.4398. Min Act: -0.0000

Data Index: 802399 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.6425. Min Act: -0.0000

Data Index: 876034 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.4359. Min Act: -0.0000

Data Index: 52868 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.1604. Min Act: -0.0000

Data Index: 134764 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.2750. Min Act: -0.0000

Data Index: 61087 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.4088. Min Act: -0.0001

Data Index: 8432 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.1002. Min Act: -0.0000

Data Index: 456734 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.0145. Min Act: -0.0000

Data Index: 762807 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.7349. Min Act: -0.0000

Data Index: 187710 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.1369. Min Act: -0.0000

Data Index: 1118836 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.8171. Min Act: -0.0000

Data Index: 888846 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.2469. Min Act: -0.0000

Data Index: 900618 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.8192. Min Act: -0.0000

Data Index: 1003599 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.7804. Min Range: -3.7804

Max Act: 3.0823. Min Act: -0.0000

Data Index: 756081 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.6317. Min Act: -0.0000

Data Index: 1285583 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.6461. Min Act: -0.0000

Data Index: 896829 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.8860. Min Act: -0.0000

Data Index: 177588 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.9875. Min Act: -0.0000

Data Index: 36235 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 3.7804. Min Range: -3.7804

Max Act: 2.8465. Min Act: -0.0000

Data Index: 777512 (C4 (Web Text))

Max Activating Token Index: 237