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

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

Neuron 364 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: 3.4593. Min Range: -3.4593

Max Act: 3.4593. Min Act: -0.1700

Data Index: 866683 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.4163. Min Act: -0.1700

Data Index: 705999 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3992. Min Act: -0.1700

Data Index: 428450 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3719. Min Act: -0.1700

Data Index: 749909 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3337. Min Act: -0.1700

Data Index: 451647 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3481. Min Act: -0.1700

Data Index: 680256 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3232. Min Act: -0.1700

Data Index: 212294 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3239. Min Act: -0.1700

Data Index: 1163320 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3035. Min Act: -0.1700

Data Index: 601585 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3189. Min Act: -0.1700

Data Index: 6025 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.3026. Min Act: -0.1700

Data Index: 338332 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1246452 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2869. Min Act: -0.1700

Data Index: 113651 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2668. Min Act: -0.1700

Data Index: 775844 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2684. Min Act: -0.1700

Data Index: 994481 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2594. Min Act: -0.1700

Data Index: 946545 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2717. Min Act: -0.1700

Data Index: 726864 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2548. Min Act: -0.1700

Data Index: 327779 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2694. Min Act: -0.1700

Data Index: 121796 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 3.4593. Min Range: -3.4593

Max Act: 3.2764. Min Act: -0.1700

Data Index: 687541 (C4 (Web Text))

Max Activating Token Index: 569