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

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

Neuron 2335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.7220. Min Act: -0.0000

Data Index: 1392559 (Python Code)

Max Activating Token Index: 194

Text #1

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.6465. Min Act: -0.0000

Data Index: 1518985 (Python Code)

Max Activating Token Index: 79

Text #2

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.3862. Min Act: -0.0000

Data Index: 1518505 (Python Code)

Max Activating Token Index: 248

Text #3

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.5405. Min Act: -0.0000

Data Index: 1637508 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.3686. Min Act: -0.0000

Data Index: 1602724 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.2499. Min Act: -0.0000

Data Index: 1631348 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.3898. Min Act: -0.0000

Data Index: 1535610 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.2638. Min Act: -0.0000

Data Index: 1572949 (Python Code)

Max Activating Token Index: 179

Text #8

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.4329. Min Act: -0.0000

Data Index: 1381085 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.4040. Min Act: -0.0000

Data Index: 1443566 (Python Code)

Max Activating Token Index: 910

Text #10

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0304. Min Act: -0.0000

Data Index: 1587876 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.1800. Min Act: -0.0000

Data Index: 1497732 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0970. Min Act: -0.0000

Data Index: 1545023 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0654. Min Act: -0.0000

Data Index: 1633843 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0457. Min Act: -0.0000

Data Index: 1447911 (Python Code)

Max Activating Token Index: 615

Text #15

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.2374. Min Act: -0.0000

Data Index: 1612353 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0347. Min Act: -0.0000

Data Index: 1484927 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0172. Min Act: -0.0000

Data Index: 1643365 (Python Code)

Max Activating Token Index: 695

Text #18

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.0063. Min Act: -0.0000

Data Index: 1610997 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 4.7220. Min Range: -4.7220

Max Act: 4.1060. Min Act: -0.0000

Data Index: 1382533 (Python Code)

Max Activating Token Index: 663