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

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

Neuron 220 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: 3.6529. Min Range: -3.6529

Max Act: 3.6529. Min Act: -0.1700

Data Index: 1046855 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.6467. Min Act: -0.1700

Data Index: 969947 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5612. Min Act: -0.1699

Data Index: 1298632 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5280. Min Act: -0.1700

Data Index: 1750 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5289. Min Act: -0.1700

Data Index: 1044456 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5033. Min Act: -0.1700

Data Index: 580904 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5074. Min Act: -0.1700

Data Index: 914775 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5110. Min Act: -0.1700

Data Index: 858644 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5079. Min Act: -0.1700

Data Index: 1286047 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5186. Min Act: -0.1696

Data Index: 1003280 (C4 (Web Text))

Max Activating Token Index: 315

Text #10

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.5026. Min Act: -0.1696

Data Index: 279598 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4890. Min Act: -0.1700

Data Index: 293256 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4878. Min Act: -0.1700

Data Index: 785111 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4772. Min Act: -0.1700

Data Index: 451305 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1298346 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4694. Min Act: -0.1700

Data Index: 1001416 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4503. Min Act: -0.1700

Data Index: 291315 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4323. Min Act: -0.1700

Data Index: 1065251 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4286. Min Act: -0.1700

Data Index: 596545 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.6529. Min Range: -3.6529

Max Act: 3.4319. Min Act: -0.1700

Data Index: 275430 (C4 (Web Text))

Max Activating Token Index: 194