Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 350 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0803. Min Act: -0.1700

Data Index: 1027004 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0330. Min Act: -0.1700

Data Index: 777562 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0172. Min Act: -0.1700

Data Index: 961306 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1113423 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1184374 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 428189 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 97920 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 560924 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 1220106 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0172. Min Act: -0.1700

Data Index: 1093283 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 939413 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 519615 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 555022 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 3.0803. Min Range: -3.0803

Max Act: 3.0014. Min Act: -0.1700

Data Index: 1097130 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9697. Min Act: -0.1700

Data Index: 1097078 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9697. Min Act: -0.1700

Data Index: 214888 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 272136 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 767900 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 1150976 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 3.0803. Min Range: -3.0803

Max Act: 2.9856. Min Act: -0.1700

Data Index: 289186 (C4 (Web Text))

Max Activating Token Index: 213