Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 2044 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.7246. Min Act: -0.1700

Data Index: 279504 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.7110. Min Act: -0.1700

Data Index: 209219 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6805. Min Act: -0.1700

Data Index: 629067 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6943. Min Act: -0.1700

Data Index: 469177 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6938. Min Act: -0.1700

Data Index: 300953 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6743. Min Act: -0.1700

Data Index: 443426 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6787. Min Act: -0.1700

Data Index: 1119517 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6441. Min Act: -0.1700

Data Index: 922726 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1079439 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6425. Min Act: -0.1700

Data Index: 691515 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6104. Min Act: -0.1700

Data Index: 343478 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6330. Min Act: -0.1700

Data Index: 1238266 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6379. Min Act: -0.1700

Data Index: 1085470 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6331. Min Act: -0.1700

Data Index: 612974 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.5994. Min Act: -0.1700

Data Index: 143100 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.5871. Min Act: -0.1700

Data Index: 56838 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.6096. Min Act: -0.1700

Data Index: 678910 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.5860. Min Act: -0.1700

Data Index: 1134491 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.5960. Min Act: -0.1700

Data Index: 268016 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 3.7246. Min Range: -3.7246

Max Act: 3.5967. Min Act: -0.1700

Data Index: 1132426 (C4 (Web Text))

Max Activating Token Index: 855