Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 895 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2851. Min Act: -0.0000

Data Index: 1644780 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2721. Min Act: -0.0000

Data Index: 1449746 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1649947 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2610. Min Act: -0.0001

Data Index: 1622377 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1436959 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1507185 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1437070 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1641984 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2368. Min Act: -0.0001

Data Index: 1386285 (Python Code)

Max Activating Token Index: 345

Text #9

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1637707 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2102. Min Act: 0.0000

Data Index: 1643553 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1616454 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1407183 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2106. Min Act: 0.0000

Data Index: 1470982 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2004. Min Act: 0.0000

Data Index: 1441306 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2101. Min Act: 0.0000

Data Index: 1567031 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1516696 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1361027 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1485835 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.2851. Min Range: -0.2851

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1404648 (Python Code)

Max Activating Token Index: 238