Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1494 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0740. Min Act: -0.1700

Data Index: 1318630 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.1052. Min Act: -0.1700

Data Index: 300108 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0427. Min Act: -0.1700

Data Index: 1088619 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0740. Min Act: -0.1700

Data Index: 591056 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 558834 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1352399 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0740. Min Act: -0.1700

Data Index: 962138 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0427. Min Act: -0.1700

Data Index: 995439 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1229965 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0427. Min Act: -0.1700

Data Index: 492126 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9802. Min Act: -0.1700

Data Index: 27647 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 379081 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9802. Min Act: -0.1700

Data Index: 662259 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9802. Min Act: -0.1700

Data Index: 107728 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9802. Min Act: -0.1700

Data Index: 32031 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 832943 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 691512 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 5.1052. Min Range: -5.1052

Max Act: 5.0115. Min Act: -0.1700

Data Index: 1116310 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9802. Min Act: -0.1700

Data Index: 1213870 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.1052. Min Range: -5.1052

Max Act: 4.9177. Min Act: -0.1700

Data Index: 811357 (C4 (Web Text))

Max Activating Token Index: 873