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

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

Neuron 1716 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: 6.9846. Min Range: -6.9846

Max Act: 6.9846. Min Act: -0.1700

Data Index: 505727 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.8718. Min Act: -0.1700

Data Index: 829869 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.8587. Min Act: -0.1699

Data Index: 579949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.7168. Min Act: -0.1700

Data Index: 238353 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6884. Min Act: -0.1699

Data Index: 1161749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6704. Min Act: -0.1700

Data Index: 1075909 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6417. Min Act: -0.1700

Data Index: 703669 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6572. Min Act: -0.1700

Data Index: 340646 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6129. Min Act: -0.1699

Data Index: 170705 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6093. Min Act: -0.1693

Data Index: 189728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5865. Min Act: -0.1700

Data Index: 19989 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.6196. Min Act: -0.1700

Data Index: 1341254 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.4855. Min Act: -0.1699

Data Index: 977965 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5461. Min Act: -0.1700

Data Index: 613551 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5136. Min Act: -0.1699

Data Index: 1023882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5409. Min Act: -0.1670

Data Index: 470352 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5531. Min Act: -0.1700

Data Index: 490308 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5196. Min Act: -0.1700

Data Index: 571779 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5354. Min Act: -0.1686

Data Index: 30391 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 6.9846. Min Range: -6.9846

Max Act: 6.5545. Min Act: -0.1700

Data Index: 918451 (C4 (Web Text))

Max Activating Token Index: 918