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

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

Neuron 460 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: 4.1283. Min Range: -4.1283

Max Act: 4.1283. Min Act: -0.1700

Data Index: 54224 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 4.1283. Min Range: -4.1283

Max Act: 4.0877. Min Act: -0.1700

Data Index: 1158564 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 4.1283. Min Range: -4.1283

Max Act: 4.0301. Min Act: -0.1700

Data Index: 399413 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 4.1283. Min Range: -4.1283

Max Act: 4.0069. Min Act: -0.1700

Data Index: 827834 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 4.1283. Min Range: -4.1283

Max Act: 4.0310. Min Act: -0.1700

Data Index: 55171 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 4.1283. Min Range: -4.1283

Max Act: 4.0033. Min Act: -0.1700

Data Index: 204119 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9798. Min Act: -0.1700

Data Index: 580015 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9794. Min Act: -0.1700

Data Index: 45135 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9292. Min Act: -0.1700

Data Index: 1289915 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9534. Min Act: -0.1700

Data Index: 16908 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9351. Min Act: -0.1700

Data Index: 222870 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9349. Min Act: -0.1700

Data Index: 164456 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.9114. Min Act: -0.1700

Data Index: 593259 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8859. Min Act: -0.1700

Data Index: 814426 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8628. Min Act: -0.1700

Data Index: 1193858 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8780. Min Act: -0.1700

Data Index: 1325553 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8671. Min Act: -0.1700

Data Index: 1171893 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8727. Min Act: -0.1700

Data Index: 401819 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8783. Min Act: -0.1700

Data Index: 600926 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 4.1283. Min Range: -4.1283

Max Act: 3.8846. Min Act: -0.1700

Data Index: 1302356 (C4 (Web Text))

Max Activating Token Index: 996