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

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

Neuron 56 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: 4.1195. Min Range: -4.1195

Max Act: 4.1195. Min Act: -0.1700

Data Index: 721104 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0968. Min Act: -0.1700

Data Index: 451298 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0579. Min Act: -0.1700

Data Index: 503106 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9890. Min Act: -0.1700

Data Index: 402056 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0486. Min Act: -0.1700

Data Index: 1085937 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0544. Min Act: -0.1700

Data Index: 411445 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0072. Min Act: -0.1700

Data Index: 521594 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0115. Min Act: -0.1700

Data Index: 1132524 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9619. Min Act: -0.1700

Data Index: 56402 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9648. Min Act: -0.1700

Data Index: 104253 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9871. Min Act: -0.1700

Data Index: 372326 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9722. Min Act: -0.1700

Data Index: 452649 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9613. Min Act: -0.1700

Data Index: 644583 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 4.1195. Min Range: -4.1195

Max Act: 4.0074. Min Act: -0.1700

Data Index: 915376 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9966. Min Act: -0.1700

Data Index: 1121842 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9399. Min Act: -0.1700

Data Index: 577879 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9861. Min Act: -0.1700

Data Index: 958920 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9815. Min Act: -0.1700

Data Index: 949805 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9401. Min Act: -0.1700

Data Index: 1460663 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 4.1195. Min Range: -4.1195

Max Act: 3.9471. Min Act: -0.1700

Data Index: 607943 (C4 (Web Text))

Max Activating Token Index: 208