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

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

Neuron 902 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: 3.8997. Min Range: -3.8997

Max Act: 3.8997. Min Act: -0.1700

Data Index: 391169 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8944. Min Act: -0.1700

Data Index: 1194095 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8924. Min Act: -0.1700

Data Index: 172058 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8329. Min Act: -0.1700

Data Index: 1160585 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.8383. Min Act: -0.1700

Data Index: 920724 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7863. Min Act: -0.1700

Data Index: 319253 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7858. Min Act: -0.1700

Data Index: 730237 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7895. Min Act: -0.1700

Data Index: 1355493 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7673. Min Act: -0.1700

Data Index: 1233093 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7766. Min Act: -0.1700

Data Index: 486670 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7742. Min Act: -0.1700

Data Index: 583232 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7539. Min Act: -0.1700

Data Index: 994652 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7578. Min Act: -0.1700

Data Index: 463545 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7556. Min Act: -0.1700

Data Index: 37209 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7482. Min Act: -0.1700

Data Index: 1129884 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7406. Min Act: -0.1700

Data Index: 115855 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7318. Min Act: -0.1700

Data Index: 556045 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7513. Min Act: -0.1700

Data Index: 231590 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7479. Min Act: -0.1700

Data Index: 150515 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 3.8997. Min Range: -3.8997

Max Act: 3.7309. Min Act: -0.1700

Data Index: 496114 (C4 (Web Text))

Max Activating Token Index: 970