Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 149 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.6334. Min Act: -0.1699

Data Index: 1531667 (Python Code)

Max Activating Token Index: 446

Text #1

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.4459. Min Act: -0.1699

Data Index: 1450519 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.4772. Min Act: -0.1700

Data Index: 1404537 (Python Code)

Max Activating Token Index: 519

Text #3

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.4147. Min Act: -0.1700

Data Index: 1451750 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.4147. Min Act: -0.1700

Data Index: 1635937 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.4147. Min Act: -0.1700

Data Index: 431678 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.3209. Min Act: -0.1700

Data Index: 1448652 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.3209. Min Act: -0.1700

Data Index: 1400112 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2897. Min Act: -0.1700

Data Index: 1153534 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2897. Min Act: -0.1700

Data Index: 1441966 (Python Code)

Max Activating Token Index: 447

Text #10

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2897. Min Act: -0.1700

Data Index: 1457994 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.3209. Min Act: -0.1700

Data Index: 209267 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2272. Min Act: -0.1700

Data Index: 1417521 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2584. Min Act: -0.1700

Data Index: 1621036 (Python Code)

Max Activating Token Index: 775

Text #14

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2584. Min Act: -0.1700

Data Index: 1418623 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.1959. Min Act: -0.1700

Data Index: 238585 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.1647. Min Act: -0.1700

Data Index: 1390788 (Python Code)

Max Activating Token Index: 242

Text #17

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2272. Min Act: -0.1699

Data Index: 1378874 (Python Code)

Max Activating Token Index: 602

Text #18

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.1959. Min Act: -0.1700

Data Index: 1372641 (Python Code)

Max Activating Token Index: 590

Text #19

Max Range: 7.6334. Min Range: -7.6334

Max Act: 7.2272. Min Act: -0.1700

Data Index: 1353513 (C4 (Web Text))

Max Activating Token Index: 550