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

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

Neuron 4547 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1050985 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1480. Min Act: -0.0001

Data Index: 731459 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1622. Min Act: -0.0001

Data Index: 187274 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1623. Min Act: -0.0001

Data Index: 919591 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1504. Min Act: -0.0001

Data Index: 964218 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1545. Min Act: -0.0001

Data Index: 352827 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1329. Min Act: -0.0001

Data Index: 844000 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1588. Min Act: -0.0001

Data Index: 602540 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1527. Min Act: -0.0001

Data Index: 785737 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1377. Min Act: -0.0001

Data Index: 727310 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1482. Min Act: -0.0001

Data Index: 994190 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1402. Min Act: -0.0001

Data Index: 615223 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1297940 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1515. Min Act: -0.0001

Data Index: 135010 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1353. Min Act: -0.0001

Data Index: 765237 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1453008 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1259855 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1334. Min Act: -0.0001

Data Index: 469835 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1544275 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1324. Min Act: -0.0001

Data Index: 578372 (C4 (Web Text))

Max Activating Token Index: 565