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

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

Neuron 2891 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: 0.0773. Min Range: -0.0773

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1442515 (Python Code)

Max Activating Token Index: 894

Text #1

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1604677 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0488. Min Act: -0.0000

Data Index: 793906 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0380. Min Act: -0.0000

Data Index: 62577 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1499389 (Python Code)

Max Activating Token Index: 279

Text #5

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0359. Min Act: -0.0000

Data Index: 575120 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0322. Min Act: -0.0000

Data Index: 425766 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0330. Min Act: -0.0000

Data Index: 580595 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0147. Min Act: -0.0000

Data Index: 1617777 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0321. Min Act: -0.0000

Data Index: 402551 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0318. Min Act: -0.0000

Data Index: 102411 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0306. Min Act: -0.0001

Data Index: 249861 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1054376 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1534950 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0305. Min Act: -0.0000

Data Index: 43660 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0269. Min Act: -0.0000

Data Index: 891395 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0285. Min Act: -0.0000

Data Index: 307986 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1174913 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0307. Min Act: -0.0000

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.0773. Min Range: -0.0773

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1190749 (C4 (Web Text))

Max Activating Token Index: 502