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

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

Neuron 1526 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: 3.7268. Min Range: -3.7268

Max Act: 3.7268. Min Act: -0.1700

Data Index: 817830 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6859. Min Act: -0.1700

Data Index: 198105 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6434. Min Act: -0.1700

Data Index: 1039561 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6302. Min Act: -0.1699

Data Index: 1099684 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6287. Min Act: -0.1700

Data Index: 940594 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6052. Min Act: -0.1700

Data Index: 156091 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6074. Min Act: -0.1700

Data Index: 333973 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5775. Min Act: -0.1700

Data Index: 188336 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.6010. Min Act: -0.1700

Data Index: 13706 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5910. Min Act: -0.1700

Data Index: 807899 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5726. Min Act: -0.1700

Data Index: 583018 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5611. Min Act: -0.1700

Data Index: 635320 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5603. Min Act: -0.1700

Data Index: 456044 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5395. Min Act: -0.1700

Data Index: 1096557 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5325. Min Act: -0.1698

Data Index: 128490 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5481. Min Act: -0.1700

Data Index: 693151 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5302. Min Act: -0.1700

Data Index: 756094 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5315. Min Act: -0.1700

Data Index: 405329 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5221. Min Act: -0.1700

Data Index: 908176 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 3.7268. Min Range: -3.7268

Max Act: 3.5111. Min Act: -0.1699

Data Index: 206794 (C4 (Web Text))

Max Activating Token Index: 935