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

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

Neuron 17 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: 7.4483. Min Range: -7.4483

Max Act: 7.4483. Min Act: -0.1700

Data Index: 837175 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 7.4483. Min Range: -7.4483

Max Act: 7.1983. Min Act: -0.1700

Data Index: 1058082 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.8858. Min Act: -0.1700

Data Index: 678522 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.8546. Min Act: -0.1700

Data Index: 54657 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.8858. Min Act: -0.1700

Data Index: 631368 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.8233. Min Act: -0.1700

Data Index: 244033 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7921. Min Act: -0.1700

Data Index: 1251969 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7296. Min Act: -0.1700

Data Index: 984259 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7921. Min Act: -0.1700

Data Index: 1287193 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7921. Min Act: -0.1700

Data Index: 1133762 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7608. Min Act: -0.1698

Data Index: 1156655 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7921. Min Act: -0.1700

Data Index: 900569 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7921. Min Act: -0.1700

Data Index: 521077 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.6983. Min Act: -0.1699

Data Index: 1013698 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7296. Min Act: -0.1700

Data Index: 1073770 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.6983. Min Act: -0.1700

Data Index: 387755 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.7608. Min Act: -0.1700

Data Index: 1217130 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.6983. Min Act: -0.1700

Data Index: 946029 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.6983. Min Act: -0.1700

Data Index: 430959 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 7.4483. Min Range: -7.4483

Max Act: 6.6983. Min Act: -0.1700

Data Index: 35657 (C4 (Web Text))

Max Activating Token Index: 58