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

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

Neuron 5007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.7260. Min Act: -0.0001

Data Index: 1493106 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.3528. Min Act: -0.0001

Data Index: 1499788 (Python Code)

Max Activating Token Index: 740

Text #2

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.0663. Min Act: -0.0000

Data Index: 1383168 (Python Code)

Max Activating Token Index: 383

Text #3

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.1865. Min Act: -0.0001

Data Index: 1451556 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.0134. Min Act: -0.0000

Data Index: 1420481 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.3338. Min Act: -0.0001

Data Index: 1627445 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.2491. Min Act: -0.0001

Data Index: 1617999 (Python Code)

Max Activating Token Index: 54

Text #7

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.8443. Min Act: -0.0000

Data Index: 1361601 (Python Code)

Max Activating Token Index: 142

Text #8

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9743. Min Act: -0.0000

Data Index: 1445251 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 4.7260. Min Range: -4.7260

Max Act: 4.1277. Min Act: -0.0001

Data Index: 1464532 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9654. Min Act: -0.0000

Data Index: 1612126 (Python Code)

Max Activating Token Index: 480

Text #11

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9636. Min Act: -0.0001

Data Index: 1475281 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9347. Min Act: -0.0000

Data Index: 1458396 (Python Code)

Max Activating Token Index: 588

Text #13

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9273. Min Act: -0.0001

Data Index: 1531329 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.8830. Min Act: -0.0000

Data Index: 1594976 (Python Code)

Max Activating Token Index: 17

Text #15

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.7017. Min Act: -0.0001

Data Index: 1411741 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.8582. Min Act: -0.0001

Data Index: 1483626 (Python Code)

Max Activating Token Index: 62

Text #17

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.8442. Min Act: -0.0000

Data Index: 1528613 (Python Code)

Max Activating Token Index: 435

Text #18

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.9944. Min Act: -0.0001

Data Index: 1430783 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 4.7260. Min Range: -4.7260

Max Act: 3.8329. Min Act: -0.0001

Data Index: 1560315 (Python Code)

Max Activating Token Index: 974