Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1160 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.4262. Min Act: -0.1700

Data Index: 773735 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3325. Min Act: -0.1700

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3325. Min Act: -0.1700

Data Index: 671451 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1167988 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1254762 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3637. Min Act: -0.1700

Data Index: 715815 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1131831 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 691433 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1160684 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1178465 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2700. Min Act: -0.1700

Data Index: 863142 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2700. Min Act: -0.1700

Data Index: 105681 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1358199 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1330742 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2075. Min Act: -0.1700

Data Index: 629894 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1234492 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1139638 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.2387. Min Act: -0.1700

Data Index: 1180645 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.1450. Min Act: -0.1700

Data Index: 717276 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 5.4262. Min Range: -5.4262

Max Act: 5.1762. Min Act: -0.1700

Data Index: 1208515 (C4 (Web Text))

Max Activating Token Index: 750