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

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

Neuron 208 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: 3.6845. Min Range: -3.6845

Max Act: 3.6845. Min Act: -0.1700

Data Index: 1336454 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.6336. Min Act: -0.1700

Data Index: 1609342 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.6186. Min Act: -0.1700

Data Index: 948396 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5739. Min Act: -0.1700

Data Index: 951103 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5799. Min Act: -0.1700

Data Index: 1110351 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.6011. Min Act: -0.1700

Data Index: 1509140 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5833. Min Act: -0.1700

Data Index: 23091 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5709. Min Act: -0.1699

Data Index: 1301054 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1092053 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5846. Min Act: -0.1700

Data Index: 8963 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5545. Min Act: -0.1700

Data Index: 9553 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5504. Min Act: -0.1700

Data Index: 272628 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5418. Min Act: -0.1700

Data Index: 194659 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5302. Min Act: -0.1700

Data Index: 344763 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.4984. Min Act: -0.1700

Data Index: 696984 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5023. Min Act: -0.1700

Data Index: 812418 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.4780. Min Act: -0.1700

Data Index: 322303 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.4834. Min Act: -0.1700

Data Index: 1483050 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.4722. Min Act: -0.1700

Data Index: 1447788 (Python Code)

Max Activating Token Index: 767

Text #19

Max Range: 3.6845. Min Range: -3.6845

Max Act: 3.5229. Min Act: -0.1700

Data Index: 452422 (C4 (Web Text))

Max Activating Token Index: 925