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

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

Neuron 314 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4964. Min Act: -0.1700

Data Index: 618139 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.5277. Min Act: -0.1700

Data Index: 423895 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4964. Min Act: -0.1700

Data Index: 1297491 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4652. Min Act: -0.1699

Data Index: 861269 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3714. Min Act: -0.1700

Data Index: 377196 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3089. Min Act: -0.1700

Data Index: 1184024 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4027. Min Act: -0.1700

Data Index: 628611 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4027. Min Act: -0.1700

Data Index: 446227 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 334941 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3714. Min Act: -0.1700

Data Index: 33396 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3714. Min Act: -0.1700

Data Index: 445276 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3714. Min Act: -0.1700

Data Index: 188829 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 95694 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 433850 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 1116297 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 1338567 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3402. Min Act: -0.1700

Data Index: 171876 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.4027. Min Act: -0.1700

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.3089. Min Act: -0.1700

Data Index: 344418 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 5.5277. Min Range: -5.5277

Max Act: 5.2777. Min Act: -0.1700

Data Index: 1046854 (C4 (Web Text))

Max Activating Token Index: 677