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

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

Neuron 539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.2521. Min Act: -0.1700

Data Index: 763424 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.1896. Min Act: -0.1700

Data Index: 881164 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.1271. Min Act: -0.1700

Data Index: 1296186 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0958. Min Act: -0.1700

Data Index: 83850 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0958. Min Act: -0.1700

Data Index: 280691 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0646. Min Act: -0.1700

Data Index: 1163665 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0646. Min Act: -0.1700

Data Index: 1310199 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0646. Min Act: -0.1700

Data Index: 1073210 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0333. Min Act: -0.1700

Data Index: 88474 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0958. Min Act: -0.1700

Data Index: 13630 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0958. Min Act: -0.1700

Data Index: 1210200 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9396. Min Act: -0.1700

Data Index: 937976 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 5.2521. Min Range: -5.2521

Max Act: 5.0021. Min Act: -0.1700

Data Index: 192529 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9708. Min Act: -0.1700

Data Index: 1188726 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9708. Min Act: -0.1700

Data Index: 1263944 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9396. Min Act: -0.1700

Data Index: 1337040 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9396. Min Act: -0.1700

Data Index: 375327 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9708. Min Act: -0.1700

Data Index: 693886 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9083. Min Act: -0.1700

Data Index: 480024 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 5.2521. Min Range: -5.2521

Max Act: 4.9708. Min Act: -0.1700

Data Index: 1019645 (C4 (Web Text))

Max Activating Token Index: 303