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

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

Neuron 1810 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: 4.1897. Min Range: -4.1897

Max Act: 4.1897. Min Act: -0.1700

Data Index: 11085 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0646. Min Act: -0.1700

Data Index: 1301553 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0646. Min Act: -0.1700

Data Index: 680647 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0334. Min Act: -0.1700

Data Index: 176474 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0334. Min Act: -0.1700

Data Index: 831789 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0334. Min Act: -0.1699

Data Index: 1101802 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 4.1897. Min Range: -4.1897

Max Act: 4.0021. Min Act: -0.1700

Data Index: 276494 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9708. Min Act: -0.1700

Data Index: 731757 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9708. Min Act: -0.1700

Data Index: 945292 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9708. Min Act: -0.1700

Data Index: 267319 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9708. Min Act: -0.1700

Data Index: 159117 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9396. Min Act: -0.1700

Data Index: 686367 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9708. Min Act: -0.1699

Data Index: 540913 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9396. Min Act: -0.1700

Data Index: 161473 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9083. Min Act: -0.1700

Data Index: 105486 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.8770. Min Act: -0.1700

Data Index: 370422 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9083. Min Act: -0.1700

Data Index: 115378 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9083. Min Act: -0.1700

Data Index: 929176 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.9083. Min Act: -0.1700

Data Index: 422626 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 4.1897. Min Range: -4.1897

Max Act: 3.8770. Min Act: -0.1700

Data Index: 594162 (C4 (Web Text))

Max Activating Token Index: 45