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

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

Neuron 1397 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: 2.8918. Min Range: -2.8918

Max Act: 2.8918. Min Act: -0.1700

Data Index: 706552 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8903. Min Act: -0.1700

Data Index: 316240 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8522. Min Act: -0.1674

Data Index: 1062813 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8444. Min Act: -0.1699

Data Index: 1332790 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8364. Min Act: -0.1700

Data Index: 387450 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8368. Min Act: -0.1700

Data Index: 944162 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8355. Min Act: -0.1696

Data Index: 155352 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8240. Min Act: -0.1700

Data Index: 88081 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8053. Min Act: -0.1700

Data Index: 88555 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8002. Min Act: -0.1700

Data Index: 857348 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7976. Min Act: -0.1700

Data Index: 878056 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7933. Min Act: -0.1700

Data Index: 1072923 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.8017. Min Act: -0.1667

Data Index: 1336352 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7790. Min Act: -0.1700

Data Index: 686134 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7799. Min Act: -0.1699

Data Index: 1303811 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7634. Min Act: -0.1700

Data Index: 1395347 (Python Code)

Max Activating Token Index: 245

Text #16

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7665. Min Act: -0.1700

Data Index: 1044924 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7679. Min Act: -0.1700

Data Index: 240963 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7688. Min Act: -0.1698

Data Index: 1042766 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 2.8918. Min Range: -2.8918

Max Act: 2.7710. Min Act: -0.1697

Data Index: 363431 (C4 (Web Text))

Max Activating Token Index: 191