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

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

Neuron 2120 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.4278. Min Act: -0.0000

Data Index: 63643 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3533. Min Act: -0.0000

Data Index: 333577 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3617. Min Act: -0.0000

Data Index: 347934 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1409996 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3188. Min Act: -0.0000

Data Index: 662218 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1492318 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3117. Min Act: -0.0000

Data Index: 1429407 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1486897 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1452542 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1491503 (Python Code)

Max Activating Token Index: 560

Text #10

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2985. Min Act: -0.0000

Data Index: 1382955 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1306392 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1296791 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2986. Min Act: -0.0000

Data Index: 1367606 (Python Code)

Max Activating Token Index: 471

Text #14

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2873. Min Act: -0.0000

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2963. Min Act: -0.0000

Data Index: 855047 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2875. Min Act: -0.0000

Data Index: 995440 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1404632 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.4278. Min Range: -0.4278

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1467645 (Python Code)

Max Activating Token Index: 228