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

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

Neuron 728 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: 4.1385. Min Range: -4.1385

Max Act: 4.1385. Min Act: -0.1699

Data Index: 665374 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 4.1385. Min Range: -4.1385

Max Act: 4.0340. Min Act: -0.1700

Data Index: 11430 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 4.1385. Min Range: -4.1385

Max Act: 4.0462. Min Act: -0.1700

Data Index: 310828 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9965. Min Act: -0.1699

Data Index: 1112066 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9898. Min Act: -0.1700

Data Index: 518773 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9867. Min Act: -0.1700

Data Index: 910519 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9215. Min Act: -0.1700

Data Index: 845977 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9314. Min Act: -0.1700

Data Index: 535976 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8941. Min Act: -0.1699

Data Index: 1448913 (Python Code)

Max Activating Token Index: 871

Text #9

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.9068. Min Act: -0.1699

Data Index: 128520 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8890. Min Act: -0.1700

Data Index: 1038806 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8794. Min Act: -0.1700

Data Index: 357220 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8797. Min Act: -0.1700

Data Index: 118207 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8788. Min Act: -0.1700

Data Index: 276892 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8575. Min Act: -0.1699

Data Index: 617430 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8393. Min Act: -0.1700

Data Index: 178082 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8352. Min Act: -0.1699

Data Index: 60845 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8509. Min Act: -0.1700

Data Index: 504506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8293. Min Act: -0.1699

Data Index: 964771 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 4.1385. Min Range: -4.1385

Max Act: 3.8326. Min Act: -0.1700

Data Index: 1041036 (C4 (Web Text))

Max Activating Token Index: 1010