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

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

Neuron 1524 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: 3.1320. Min Range: -3.1320

Max Act: 3.1320. Min Act: -0.1700

Data Index: 718494 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.1163. Min Act: -0.1700

Data Index: 1496464 (Python Code)

Max Activating Token Index: 684

Text #2

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.1005. Min Act: -0.1700

Data Index: 592918 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1571721 (Python Code)

Max Activating Token Index: 166

Text #4

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1200189 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0690. Min Act: -0.1700

Data Index: 112180 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1591687 (Python Code)

Max Activating Token Index: 485

Text #7

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0532. Min Act: -0.1700

Data Index: 1410646 (Python Code)

Max Activating Token Index: 262

Text #8

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1381745 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0216. Min Act: -0.1700

Data Index: 85265 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0058. Min Act: -0.1700

Data Index: 383416 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0058. Min Act: -0.1700

Data Index: 580829 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0058. Min Act: -0.1700

Data Index: 110613 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 3.1320. Min Range: -3.1320

Max Act: 2.9900. Min Act: -0.1700

Data Index: 710500 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 3.1320. Min Range: -3.1320

Max Act: 2.9900. Min Act: -0.1700

Data Index: 21242 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0058. Min Act: -0.1700

Data Index: 896924 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 3.1320. Min Range: -3.1320

Max Act: 3.0058. Min Act: -0.1700

Data Index: 348681 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 3.1320. Min Range: -3.1320

Max Act: 2.9742. Min Act: -0.1700

Data Index: 406764 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 3.1320. Min Range: -3.1320

Max Act: 2.9742. Min Act: -0.1700

Data Index: 880723 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.1320. Min Range: -3.1320

Max Act: 2.9900. Min Act: -0.1700

Data Index: 1312968 (C4 (Web Text))

Max Activating Token Index: 229