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

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

Neuron 1891 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: 5.0689. Min Range: -5.0689

Max Act: 5.0689. Min Act: -0.1700

Data Index: 552540 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.8189. Min Act: -0.1700

Data Index: 808460 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.8814. Min Act: -0.1700

Data Index: 382535 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.7876. Min Act: -0.1700

Data Index: 1052413 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.8189. Min Act: -0.1700

Data Index: 571513 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.7564. Min Act: -0.1700

Data Index: 455629 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.7876. Min Act: -0.1700

Data Index: 1129146 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6939. Min Act: -0.1700

Data Index: 625434 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6939. Min Act: -0.1700

Data Index: 744703 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6626. Min Act: -0.1700

Data Index: 980198 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6939. Min Act: -0.1700

Data Index: 1211522 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6314. Min Act: -0.1700

Data Index: 1151424 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6626. Min Act: -0.1700

Data Index: 233264 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5376. Min Act: -0.1700

Data Index: 1057740 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.6001. Min Act: -0.1700

Data Index: 903172 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5689. Min Act: -0.1700

Data Index: 833951 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5376. Min Act: -0.1700

Data Index: 1032092 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5689. Min Act: -0.1700

Data Index: 970217 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5064. Min Act: -0.1700

Data Index: 93453 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.0689. Min Range: -5.0689

Max Act: 4.5064. Min Act: -0.1700

Data Index: 57248 (C4 (Web Text))

Max Activating Token Index: 617