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

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

Neuron 443 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: 3.6859. Min Range: -3.6859

Max Act: 3.6859. Min Act: -0.1700

Data Index: 499305 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5450. Min Act: -0.1700

Data Index: 266987 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5450. Min Act: -0.1700

Data Index: 273113 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5450. Min Act: -0.1699

Data Index: 421217 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5294. Min Act: -0.1700

Data Index: 675102 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5294. Min Act: -0.1699

Data Index: 1313646 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.5137. Min Act: -0.1699

Data Index: 304053 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.4824. Min Act: -0.1699

Data Index: 1049869 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.4824. Min Act: -0.1700

Data Index: 908546 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.4353. Min Act: -0.1699

Data Index: 831021 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1090443 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3883. Min Act: -0.1700

Data Index: 1300933 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3883. Min Act: -0.1700

Data Index: 391097 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.4040. Min Act: -0.1700

Data Index: 1185402 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3883. Min Act: -0.1700

Data Index: 1346262 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3883. Min Act: -0.1700

Data Index: 881891 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3726. Min Act: -0.1700

Data Index: 347056 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3726. Min Act: -0.1700

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3412. Min Act: -0.1700

Data Index: 4059 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.6859. Min Range: -3.6859

Max Act: 3.3569. Min Act: -0.1700

Data Index: 1060067 (C4 (Web Text))

Max Activating Token Index: 555