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

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

Neuron 804 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: 7.2874. Min Range: -7.2874

Max Act: 7.2874. Min Act: -0.1700

Data Index: 23285 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2249. Min Act: -0.1700

Data Index: 1291024 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.2874. Min Act: -0.1700

Data Index: 1165442 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1624. Min Act: -0.1700

Data Index: 947975 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1624. Min Act: -0.1700

Data Index: 1024459 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1624. Min Act: -0.1700

Data Index: 15403 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1624. Min Act: -0.1700

Data Index: 966092 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.1624. Min Act: -0.1700

Data Index: 43925 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.0374. Min Act: -0.1700

Data Index: 1052822 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.0374. Min Act: -0.1700

Data Index: 914493 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.0374. Min Act: -0.1700

Data Index: 1061791 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9749. Min Act: -0.1700

Data Index: 834565 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9749. Min Act: -0.1700

Data Index: 1289823 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 7.2874. Min Range: -7.2874

Max Act: 7.0374. Min Act: -0.1699

Data Index: 99711 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9749. Min Act: -0.1699

Data Index: 890062 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9124. Min Act: -0.1700

Data Index: 698243 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9124. Min Act: -0.1700

Data Index: 165615 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.8499. Min Act: -0.1700

Data Index: 732240 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.8499. Min Act: -0.1700

Data Index: 858818 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 7.2874. Min Range: -7.2874

Max Act: 6.9124. Min Act: -0.1700

Data Index: 357665 (C4 (Web Text))

Max Activating Token Index: 690