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

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

Neuron 664 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: 3.7605. Min Range: -3.7605

Max Act: 3.7605. Min Act: -0.1700

Data Index: 1304098 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.7254. Min Act: -0.1700

Data Index: 195792 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6808. Min Act: -0.1700

Data Index: 331392 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6492. Min Act: -0.1700

Data Index: 1062963 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6375. Min Act: -0.1700

Data Index: 317629 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6390. Min Act: -0.1700

Data Index: 1184941 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6404. Min Act: -0.1700

Data Index: 230905 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6170. Min Act: -0.1700

Data Index: 1340332 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.6071. Min Act: -0.1700

Data Index: 1159125 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5958. Min Act: -0.1700

Data Index: 5516 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5900. Min Act: -0.1700

Data Index: 1044432 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5584. Min Act: -0.1700

Data Index: 1123791 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5602. Min Act: -0.1700

Data Index: 1185241 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5603. Min Act: -0.1700

Data Index: 474962 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5760. Min Act: -0.1690

Data Index: 48245 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5293. Min Act: -0.1699

Data Index: 621703 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5316. Min Act: -0.1700

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5145. Min Act: -0.1700

Data Index: 742194 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5118. Min Act: -0.1700

Data Index: 763224 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.7605. Min Range: -3.7605

Max Act: 3.5239. Min Act: -0.1700

Data Index: 531622 (C4 (Web Text))

Max Activating Token Index: 875