Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 101 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.6420. Min Act: -0.1700

Data Index: 153667 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5793. Min Act: -0.1700

Data Index: 238346 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1544928 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5637. Min Act: -0.1700

Data Index: 1248127 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5637. Min Act: -0.1700

Data Index: 945911 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 837528 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1454809 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5480. Min Act: -0.1700

Data Index: 1016414 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 155193 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 627610 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 693998 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5480. Min Act: -0.1700

Data Index: 781836 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5480. Min Act: -0.1700

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1164291 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 627200 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 1221081 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 220183 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5324. Min Act: -0.1700

Data Index: 1025964 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 49730 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 543744 (C4 (Web Text))

Max Activating Token Index: 351