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

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

Neuron 236 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: 3.7408. Min Range: -3.7408

Max Act: 3.7408. Min Act: -0.1700

Data Index: 866628 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.7105. Min Act: -0.1700

Data Index: 174658 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6622. Min Act: -0.1700

Data Index: 890592 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6752. Min Act: -0.1700

Data Index: 711185 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6647. Min Act: -0.1700

Data Index: 289051 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6639. Min Act: -0.1700

Data Index: 127036 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6740. Min Act: -0.1700

Data Index: 519478 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6575. Min Act: -0.1700

Data Index: 619635 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6376. Min Act: -0.1700

Data Index: 906730 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6399. Min Act: -0.1700

Data Index: 222393 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6363. Min Act: -0.1700

Data Index: 869385 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6605. Min Act: -0.1700

Data Index: 210793 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6339. Min Act: -0.1700

Data Index: 604993 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6390. Min Act: -0.1700

Data Index: 470336 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1045892 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.5946. Min Act: -0.1700

Data Index: 385282 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6095. Min Act: -0.1700

Data Index: 1206496 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.6165. Min Act: -0.1700

Data Index: 995233 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.5977. Min Act: -0.1700

Data Index: 297104 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.7408. Min Range: -3.7408

Max Act: 3.5647. Min Act: -0.1699

Data Index: 9138 (C4 (Web Text))

Max Activating Token Index: 484