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

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

Neuron 622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.7202. Min Act: -0.1700

Data Index: 688380 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.6576. Min Act: -0.1700

Data Index: 1182297 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5950. Min Act: -0.1700

Data Index: 306208 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5637. Min Act: -0.1700

Data Index: 713835 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5010. Min Act: -0.1700

Data Index: 1425204 (Python Code)

Max Activating Token Index: 605

Text #5

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5637. Min Act: -0.1700

Data Index: 895963 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5010. Min Act: -0.1700

Data Index: 1283394 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5324. Min Act: -0.1700

Data Index: 668322 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.5010. Min Act: -0.1700

Data Index: 364943 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4540. Min Act: -0.1700

Data Index: 1236805 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4540. Min Act: -0.1700

Data Index: 818342 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4540. Min Act: -0.1700

Data Index: 1480989 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4697. Min Act: -0.1700

Data Index: 395434 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4540. Min Act: -0.1700

Data Index: 669548 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4384. Min Act: -0.1700

Data Index: 557412 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4070. Min Act: -0.1700

Data Index: 1252290 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4227. Min Act: -0.1700

Data Index: 1357616 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.4070. Min Act: -0.1700

Data Index: 1572316 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.3442. Min Act: -0.1700

Data Index: 671085 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 3.7202. Min Range: -3.7202

Max Act: 3.3913. Min Act: -0.1700

Data Index: 1370008 (Python Code)

Max Activating Token Index: 656