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

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

Neuron 1057 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: 4.2148. Min Range: -4.2148

Max Act: 4.2148. Min Act: -0.1700

Data Index: 51897 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 4.2148. Min Range: -4.2148

Max Act: 4.1332. Min Act: -0.1700

Data Index: 104082 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 4.2148. Min Range: -4.2148

Max Act: 4.0757. Min Act: -0.1700

Data Index: 1134411 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 4.2148. Min Range: -4.2148

Max Act: 4.0344. Min Act: -0.1700

Data Index: 781019 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9999. Min Act: -0.1700

Data Index: 508811 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9815. Min Act: -0.1700

Data Index: 1251599 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9709. Min Act: -0.1700

Data Index: 32658 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9940. Min Act: -0.1700

Data Index: 71991 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9497. Min Act: -0.1700

Data Index: 589474 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9677. Min Act: -0.1700

Data Index: 149998 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9492. Min Act: -0.1700

Data Index: 1011485 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9562. Min Act: -0.1700

Data Index: 1081682 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9479. Min Act: -0.1700

Data Index: 687144 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.8877. Min Act: -0.1700

Data Index: 789900 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9348. Min Act: -0.1700

Data Index: 1036378 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9338. Min Act: -0.1700

Data Index: 1064217 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9680. Min Act: -0.1700

Data Index: 811799 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.9092. Min Act: -0.1700

Data Index: 29017 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.8615. Min Act: -0.1700

Data Index: 774021 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 4.2148. Min Range: -4.2148

Max Act: 3.8959. Min Act: -0.1700

Data Index: 775778 (C4 (Web Text))

Max Activating Token Index: 634