Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1532 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6797. Min Act: -0.1700

Data Index: 825205 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.6327. Min Act: -0.1700

Data Index: 373385 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5544. Min Act: -0.1700

Data Index: 263664 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5231. Min Act: -0.1700

Data Index: 721614 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5231. Min Act: -0.1700

Data Index: 271702 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5231. Min Act: -0.1700

Data Index: 1348123 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1080049 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5074. Min Act: -0.1700

Data Index: 1044383 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5074. Min Act: -0.1700

Data Index: 17814 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.5231. Min Act: -0.1700

Data Index: 443238 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4291. Min Act: -0.1700

Data Index: 833150 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4447. Min Act: -0.1700

Data Index: 48438 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4447. Min Act: -0.1700

Data Index: 731292 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4134. Min Act: -0.1700

Data Index: 470109 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4134. Min Act: -0.1700

Data Index: 578851 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4134. Min Act: -0.1700

Data Index: 336395 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.3977. Min Act: -0.1700

Data Index: 1117615 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4134. Min Act: -0.1700

Data Index: 252684 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.4291. Min Act: -0.1700

Data Index: 1011215 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 3.6797. Min Range: -3.6797

Max Act: 3.3977. Min Act: -0.1700

Data Index: 373173 (C4 (Web Text))

Max Activating Token Index: 813