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

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

Neuron 427 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: 4.1482. Min Range: -4.1482

Max Act: 4.1482. Min Act: -0.1700

Data Index: 39287 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 4.1482. Min Range: -4.1482

Max Act: 4.0191. Min Act: -0.1700

Data Index: 125833 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9834. Min Act: -0.1700

Data Index: 1105627 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9873. Min Act: -0.1700

Data Index: 265597 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9852. Min Act: -0.1700

Data Index: 592745 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9732. Min Act: -0.1700

Data Index: 701911 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9509. Min Act: -0.1700

Data Index: 983749 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9446. Min Act: -0.1700

Data Index: 1130473 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9276. Min Act: -0.1700

Data Index: 496819 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9363. Min Act: -0.1700

Data Index: 129815 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8939. Min Act: -0.1700

Data Index: 1089173 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9139. Min Act: -0.1700

Data Index: 243443 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9048. Min Act: -0.1700

Data Index: 487933 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9134. Min Act: -0.1700

Data Index: 1087704 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8775. Min Act: -0.1700

Data Index: 123868 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8790. Min Act: -0.1700

Data Index: 427496 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8760. Min Act: -0.1700

Data Index: 1028602 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8611. Min Act: -0.1700

Data Index: 262232 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.9019. Min Act: -0.1700

Data Index: 1020936 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 4.1482. Min Range: -4.1482

Max Act: 3.8650. Min Act: -0.1700

Data Index: 991847 (C4 (Web Text))

Max Activating Token Index: 497