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

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

Neuron 966 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: 4.1858. Min Range: -4.1858

Max Act: 4.1858. Min Act: -0.1700

Data Index: 666836 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 4.1858. Min Range: -4.1858

Max Act: 4.0338. Min Act: -0.1700

Data Index: 1068373 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 4.1858. Min Range: -4.1858

Max Act: 4.0013. Min Act: -0.1700

Data Index: 606347 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9987. Min Act: -0.1700

Data Index: 945035 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9958. Min Act: -0.1700

Data Index: 1221833 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9617. Min Act: -0.1700

Data Index: 1324387 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9220. Min Act: -0.1700

Data Index: 33905 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9092. Min Act: -0.1700

Data Index: 471164 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9409. Min Act: -0.1700

Data Index: 697334 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8852. Min Act: -0.1700

Data Index: 323171 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9067. Min Act: -0.1700

Data Index: 12396 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.9042. Min Act: -0.1700

Data Index: 449618 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8836. Min Act: -0.1700

Data Index: 221094 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8994. Min Act: -0.1700

Data Index: 1194570 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8726. Min Act: -0.1700

Data Index: 879689 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8589. Min Act: -0.1700

Data Index: 945803 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8482. Min Act: -0.1700

Data Index: 63280 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8453. Min Act: -0.1700

Data Index: 823148 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8509. Min Act: -0.1700

Data Index: 1208794 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 4.1858. Min Range: -4.1858

Max Act: 3.8625. Min Act: -0.1700

Data Index: 827006 (C4 (Web Text))

Max Activating Token Index: 972