Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 696 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.3365. Min Act: -0.1700

Data Index: 528270 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.2266. Min Act: -0.1700

Data Index: 460304 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1951. Min Act: -0.1700

Data Index: 202072 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.2108. Min Act: -0.1700

Data Index: 1518881 (Python Code)

Max Activating Token Index: 480

Text #4

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1305070 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.2108. Min Act: -0.1700

Data Index: 1616272 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1479. Min Act: -0.1700

Data Index: 66701 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1636. Min Act: -0.1700

Data Index: 1575932 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1636. Min Act: -0.1700

Data Index: 154683 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1479. Min Act: -0.1700

Data Index: 1430866 (Python Code)

Max Activating Token Index: 877

Text #10

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1164. Min Act: -0.1700

Data Index: 1628499 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1479. Min Act: -0.1700

Data Index: 692179 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.0848. Min Act: -0.1700

Data Index: 1265637 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1164. Min Act: -0.1700

Data Index: 963565 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1006. Min Act: -0.1700

Data Index: 396044 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1321. Min Act: -0.1700

Data Index: 172872 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1321. Min Act: -0.1700

Data Index: 464337 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1164. Min Act: -0.1700

Data Index: 912774 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.1164. Min Act: -0.1700

Data Index: 887491 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 3.3365. Min Range: -3.3365

Max Act: 3.0691. Min Act: -0.1700

Data Index: 710224 (C4 (Web Text))

Max Activating Token Index: 653