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

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

Neuron 369 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: 3.9079. Min Range: -3.9079

Max Act: 3.9079. Min Act: -0.1700

Data Index: 865568 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8784. Min Act: -0.1700

Data Index: 530748 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.8354. Min Act: -0.1700

Data Index: 508543 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7900. Min Act: -0.1700

Data Index: 213406 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7941. Min Act: -0.1700

Data Index: 1110206 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7893. Min Act: -0.1700

Data Index: 1103290 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7921. Min Act: -0.1700

Data Index: 1382099 (Python Code)

Max Activating Token Index: 743

Text #7

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7238. Min Act: -0.1700

Data Index: 277427 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7185. Min Act: -0.1700

Data Index: 1270825 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7151. Min Act: -0.1700

Data Index: 98709 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7041. Min Act: -0.1700

Data Index: 1560529 (Python Code)

Max Activating Token Index: 329

Text #11

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7265. Min Act: -0.1700

Data Index: 1179919 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.7148. Min Act: -0.1700

Data Index: 526877 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6905. Min Act: -0.1700

Data Index: 337731 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6986. Min Act: -0.1700

Data Index: 880410 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6891. Min Act: -0.1700

Data Index: 658645 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6633. Min Act: -0.1700

Data Index: 883927 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6507. Min Act: -0.1700

Data Index: 49044 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6475. Min Act: -0.1700

Data Index: 978001 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 3.9079. Min Range: -3.9079

Max Act: 3.6619. Min Act: -0.1700

Data Index: 1117588 (C4 (Web Text))

Max Activating Token Index: 268