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

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

Neuron 948 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: 3.0956. Min Range: -3.0956

Max Act: 3.0956. Min Act: -0.1672

Data Index: 24284 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.0956. Min Range: -3.0956

Max Act: 3.0012. Min Act: -0.1700

Data Index: 930397 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.9225. Min Act: -0.1700

Data Index: 1222596 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.9319. Min Act: -0.1700

Data Index: 206855 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.9348. Min Act: -0.1700

Data Index: 994408 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.9140. Min Act: -0.1700

Data Index: 354981 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.9052. Min Act: -0.1700

Data Index: 427591 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8968. Min Act: -0.1700

Data Index: 49564 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8960. Min Act: -0.1699

Data Index: 806350 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8824. Min Act: -0.1700

Data Index: 863965 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8725. Min Act: -0.1699

Data Index: 629252 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8766. Min Act: -0.1698

Data Index: 1141020 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8611. Min Act: -0.1700

Data Index: 125310 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8571. Min Act: -0.1699

Data Index: 556406 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8778. Min Act: -0.1700

Data Index: 1338198 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8646. Min Act: -0.1700

Data Index: 483761 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8346. Min Act: -0.1700

Data Index: 348840 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8247. Min Act: -0.1700

Data Index: 995725 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8503. Min Act: -0.1699

Data Index: 1012420 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8461. Min Act: -0.1700

Data Index: 24414 (C4 (Web Text))

Max Activating Token Index: 219