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

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

Neuron 1509 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.8037. Min Act: -0.1700

Data Index: 372592 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.5846. Min Act: -0.1700

Data Index: 694152 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.5846. Min Act: -0.1700

Data Index: 457417 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.5533. Min Act: -0.1700

Data Index: 196603 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4593. Min Act: -0.1700

Data Index: 72233 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1341261 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1575224 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4593. Min Act: -0.1700

Data Index: 377247 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4280. Min Act: -0.1700

Data Index: 93271 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4280. Min Act: -0.1700

Data Index: 515454 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4280. Min Act: -0.1700

Data Index: 775159 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3966. Min Act: -0.1700

Data Index: 1096944 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3652. Min Act: -0.1700

Data Index: 472581 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4280. Min Act: -0.1700

Data Index: 32586 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3652. Min Act: -0.1700

Data Index: 660678 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.4280. Min Act: -0.1700

Data Index: 534588 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3652. Min Act: -0.1700

Data Index: 740402 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3024. Min Act: -0.1700

Data Index: 876703 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3338. Min Act: -0.1700

Data Index: 307423 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 3.8037. Min Range: -3.8037

Max Act: 3.3652. Min Act: -0.1700

Data Index: 151917 (C4 (Web Text))

Max Activating Token Index: 552