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

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

Neuron 104 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: 5.8584. Min Range: -5.8584

Max Act: 5.8584. Min Act: -0.1700

Data Index: 943943 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.6396. Min Act: -0.1700

Data Index: 575742 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.5146. Min Act: -0.1700

Data Index: 27288 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.5771. Min Act: -0.1700

Data Index: 113609 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.5459. Min Act: -0.1700

Data Index: 717842 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4521. Min Act: -0.1700

Data Index: 636267 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.5303. Min Act: -0.1700

Data Index: 469102 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4834. Min Act: -0.1700

Data Index: 55323 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4990. Min Act: -0.1700

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4521. Min Act: -0.1700

Data Index: 544303 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4053. Min Act: -0.1700

Data Index: 521009 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3896. Min Act: -0.1700

Data Index: 101732 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3740. Min Act: -0.1700

Data Index: 757797 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4521. Min Act: -0.1700

Data Index: 213722 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3896. Min Act: -0.1700

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.4521. Min Act: -0.1700

Data Index: 315167 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3896. Min Act: -0.1699

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3896. Min Act: -0.1700

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3115. Min Act: -0.1700

Data Index: 1283989 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 5.8584. Min Range: -5.8584

Max Act: 5.3740. Min Act: -0.1700

Data Index: 346365 (C4 (Web Text))

Max Activating Token Index: 393