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

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

Neuron 1117 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.8434. Min Act: -0.1700

Data Index: 915053 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.8434. Min Act: -0.1700

Data Index: 323378 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.7184. Min Act: -0.1700

Data Index: 1070483 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.6559. Min Act: -0.1700

Data Index: 857775 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.6559. Min Act: -0.1699

Data Index: 944707 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.6247. Min Act: -0.1699

Data Index: 350180 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.5934. Min Act: -0.1700

Data Index: 609014 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.5934. Min Act: -0.1700

Data Index: 1080562 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.4997. Min Act: -0.1699

Data Index: 670941 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.3434. Min Act: -0.1700

Data Index: 773645 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.2809. Min Act: -0.1700

Data Index: 133464 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.2809. Min Act: -0.1698

Data Index: 317385 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.2497. Min Act: -0.1700

Data Index: 339345 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.1872. Min Act: -0.1700

Data Index: 979313 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.2184. Min Act: -0.1700

Data Index: 983446 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.2184. Min Act: -0.1700

Data Index: 204720 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.1872. Min Act: -0.1700

Data Index: 1056775 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.1872. Min Act: -0.1700

Data Index: 982445 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.1559. Min Act: -0.1700

Data Index: 1294 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 5.8434. Min Range: -5.8434

Max Act: 5.1559. Min Act: -0.1700

Data Index: 336916 (C4 (Web Text))

Max Activating Token Index: 969