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

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

Neuron 420 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: 3.0600. Min Range: -3.0600

Max Act: 3.0600. Min Act: -0.1700

Data Index: 426669 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 3.0600. Min Range: -3.0600

Max Act: 3.0372. Min Act: -0.1700

Data Index: 514515 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 3.0600. Min Range: -3.0600

Max Act: 3.0123. Min Act: -0.1700

Data Index: 884464 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9851. Min Act: -0.1700

Data Index: 896144 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9497. Min Act: -0.1700

Data Index: 1227409 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9354. Min Act: -0.1700

Data Index: 85242 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9471. Min Act: -0.1700

Data Index: 792209 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9488. Min Act: -0.1700

Data Index: 1087732 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9219. Min Act: -0.1700

Data Index: 384931 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9245. Min Act: -0.1700

Data Index: 345386 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9195. Min Act: -0.1700

Data Index: 2900 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9066. Min Act: -0.1700

Data Index: 900487 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9108. Min Act: -0.1700

Data Index: 1328398 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.9006. Min Act: -0.1700

Data Index: 484485 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8872. Min Act: -0.1700

Data Index: 175114 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8824. Min Act: -0.1700

Data Index: 909201 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8843. Min Act: -0.1700

Data Index: 1084170 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8692. Min Act: -0.1700

Data Index: 698535 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8793. Min Act: -0.1700

Data Index: 182134 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 3.0600. Min Range: -3.0600

Max Act: 2.8772. Min Act: -0.1700

Data Index: 1102134 (C4 (Web Text))

Max Activating Token Index: 913