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

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

Neuron 1400 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: 4.1324. Min Range: -4.1324

Max Act: 4.1324. Min Act: -0.1697

Data Index: 220747 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 4.1324. Min Range: -4.1324

Max Act: 4.0264. Min Act: -0.1697

Data Index: 944946 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 4.1324. Min Range: -4.1324

Max Act: 4.0148. Min Act: -0.1698

Data Index: 75580 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 4.1324. Min Range: -4.1324

Max Act: 4.0116. Min Act: -0.1699

Data Index: 426251 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 4.1324. Min Range: -4.1324

Max Act: 4.0078. Min Act: -0.1700

Data Index: 492030 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 4.1324. Min Range: -4.1324

Max Act: 4.0153. Min Act: -0.1698

Data Index: 1266575 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.9925. Min Act: -0.1700

Data Index: 1157449 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.9638. Min Act: -0.1700

Data Index: 200984 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.9973. Min Act: -0.1700

Data Index: 469644 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8985. Min Act: -0.1700

Data Index: 516986 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.9027. Min Act: -0.1700

Data Index: 637357 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8976. Min Act: -0.1699

Data Index: 138923 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.9012. Min Act: -0.1700

Data Index: 79609 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8675. Min Act: -0.1698

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8733. Min Act: -0.1700

Data Index: 551016 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8725. Min Act: -0.1700

Data Index: 8065 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8739. Min Act: -0.1700

Data Index: 506504 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8505. Min Act: -0.1700

Data Index: 950788 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8783. Min Act: -0.1588

Data Index: 764125 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 4.1324. Min Range: -4.1324

Max Act: 3.8627. Min Act: -0.1666

Data Index: 546743 (C4 (Web Text))

Max Activating Token Index: 797