Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1433 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0137. Min Range: -5.0137

Max Act: 5.0137. Min Act: -0.1700

Data Index: 949019 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.9512. Min Act: -0.1700

Data Index: 681730 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.8887. Min Act: -0.1700

Data Index: 131342 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.8574. Min Act: -0.1700

Data Index: 489741 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.8574. Min Act: -0.1700

Data Index: 1185262 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7949. Min Act: -0.1700

Data Index: 1227937 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7949. Min Act: -0.1700

Data Index: 1240431 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7949. Min Act: -0.1700

Data Index: 593922 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7949. Min Act: -0.1700

Data Index: 904896 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7637. Min Act: -0.1700

Data Index: 1030396 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7637. Min Act: -0.1700

Data Index: 1068325 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7324. Min Act: -0.1700

Data Index: 917710 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7637. Min Act: -0.1700

Data Index: 278095 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7324. Min Act: -0.1700

Data Index: 1092914 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7324. Min Act: -0.1700

Data Index: 697303 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7324. Min Act: -0.1699

Data Index: 153512 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.6699. Min Act: -0.1700

Data Index: 117372 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7012. Min Act: -0.1700

Data Index: 328567 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.7012. Min Act: -0.1700

Data Index: 1209162 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 5.0137. Min Range: -5.0137

Max Act: 4.6699. Min Act: -0.1700

Data Index: 287876 (C4 (Web Text))

Max Activating Token Index: 411