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

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

Neuron 326 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0595. Min Range: -7.0595

Max Act: 7.0595. Min Act: -0.1700

Data Index: 777724 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.4657. Min Act: -0.1700

Data Index: 1124152 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.3407. Min Act: -0.1700

Data Index: 1236751 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.3095. Min Act: -0.1700

Data Index: 1200662 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.3407. Min Act: -0.1700

Data Index: 1165652 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.3407. Min Act: -0.1700

Data Index: 1100828 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.2157. Min Act: -0.1700

Data Index: 265387 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.2157. Min Act: -0.1700

Data Index: 536181 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.2157. Min Act: -0.1700

Data Index: 1207868 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.2157. Min Act: -0.1700

Data Index: 589772 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1532. Min Act: -0.1700

Data Index: 712104 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1845. Min Act: -0.1700

Data Index: 166723 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1845. Min Act: -0.1700

Data Index: 1012764 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1220. Min Act: -0.1700

Data Index: 346867 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1845. Min Act: -0.1700

Data Index: 71844 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1532. Min Act: -0.1700

Data Index: 1085864 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1532. Min Act: -0.1700

Data Index: 10970 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.0907. Min Act: -0.1700

Data Index: 194501 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.0907. Min Act: -0.1700

Data Index: 1101026 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 7.0595. Min Range: -7.0595

Max Act: 6.1220. Min Act: -0.1700

Data Index: 854698 (C4 (Web Text))

Max Activating Token Index: 155