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

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

Neuron 1240 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: 3.7505. Min Range: -3.7505

Max Act: 3.7505. Min Act: -0.1700

Data Index: 201931 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.7349. Min Act: -0.1700

Data Index: 245295 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6880. Min Act: -0.1700

Data Index: 66944 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6567. Min Act: -0.1700

Data Index: 1051405 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6254. Min Act: -0.1700

Data Index: 203112 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6254. Min Act: -0.1700

Data Index: 317284 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6254. Min Act: -0.1700

Data Index: 562883 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5940. Min Act: -0.1700

Data Index: 1199843 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.6097. Min Act: -0.1700

Data Index: 1276059 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1063758 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5157. Min Act: -0.1700

Data Index: 873053 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5314. Min Act: -0.1700

Data Index: 1055068 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5157. Min Act: -0.1700

Data Index: 930930 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5001. Min Act: -0.1700

Data Index: 1006183 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5314. Min Act: -0.1700

Data Index: 465414 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.5157. Min Act: -0.1700

Data Index: 372456 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.4687. Min Act: -0.1700

Data Index: 267271 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.4687. Min Act: -0.1700

Data Index: 888200 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.4374. Min Act: -0.1700

Data Index: 103247 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 3.7505. Min Range: -3.7505

Max Act: 3.4217. Min Act: -0.1700

Data Index: 550099 (C4 (Web Text))

Max Activating Token Index: 837