Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1903 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.3060. Min Act: -0.1700

Data Index: 1372401 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2738. Min Act: -0.1700

Data Index: 1443712 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2772. Min Act: -0.1700

Data Index: 1399099 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.3005. Min Act: -0.1700

Data Index: 1432157 (Python Code)

Max Activating Token Index: 97

Text #4

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2584. Min Act: -0.1700

Data Index: 1463480 (Python Code)

Max Activating Token Index: 18

Text #5

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2546. Min Act: -0.1700

Data Index: 1511526 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2825. Min Act: -0.1700

Data Index: 1511120 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2393. Min Act: -0.1700

Data Index: 1636862 (Python Code)

Max Activating Token Index: 200

Text #8

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2555. Min Act: -0.1700

Data Index: 1621861 (Python Code)

Max Activating Token Index: 170

Text #9

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2306. Min Act: -0.1700

Data Index: 1586801 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2405. Min Act: -0.1700

Data Index: 1654650 (Python Code)

Max Activating Token Index: 634

Text #11

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2355. Min Act: -0.1700

Data Index: 1534042 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2370. Min Act: -0.1700

Data Index: 1654895 (Python Code)

Max Activating Token Index: 396

Text #13

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2262. Min Act: -0.1700

Data Index: 1540169 (Python Code)

Max Activating Token Index: 544

Text #14

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2213. Min Act: -0.1700

Data Index: 1509999 (Python Code)

Max Activating Token Index: 358

Text #15

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2277. Min Act: -0.1700

Data Index: 1410465 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2475. Min Act: -0.1700

Data Index: 1571920 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2292. Min Act: -0.1700

Data Index: 1570098 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2115. Min Act: -0.1700

Data Index: 1390981 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 4.3060. Min Range: -4.3060

Max Act: 4.2245. Min Act: -0.1700

Data Index: 1522986 (Python Code)

Max Activating Token Index: 843