Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1069 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.4384. Min Act: -0.1700

Data Index: 1520775 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.4227. Min Act: -0.1700

Data Index: 1597161 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3286. Min Act: -0.1700

Data Index: 1314956 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3443. Min Act: -0.1700

Data Index: 583094 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3443. Min Act: -0.1700

Data Index: 308304 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.3286. Min Act: -0.1700

Data Index: 330721 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2815. Min Act: -0.1700

Data Index: 523851 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2658. Min Act: -0.1700

Data Index: 930566 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2815. Min Act: -0.1700

Data Index: 542159 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1039507 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1132155 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2815. Min Act: -0.1700

Data Index: 890607 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2658. Min Act: -0.1700

Data Index: 220841 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2815. Min Act: -0.1700

Data Index: 830754 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2501. Min Act: -0.1700

Data Index: 1063190 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2501. Min Act: -0.1700

Data Index: 151769 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2501. Min Act: -0.1700

Data Index: 1520523 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1428631 (Python Code)

Max Activating Token Index: 474

Text #18

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2501. Min Act: -0.1700

Data Index: 752570 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 3.4384. Min Range: -3.4384

Max Act: 3.2501. Min Act: -0.1700

Data Index: 598971 (C4 (Web Text))

Max Activating Token Index: 89