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

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

Neuron 238 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.1990. Min Act: -0.1700

Data Index: 205066 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.1361. Min Act: -0.1700

Data Index: 964555 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0414. Min Act: -0.1700

Data Index: 395607 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0730. Min Act: -0.1700

Data Index: 1251534 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 448180 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1700

Data Index: 254216 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 952584 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 127447 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 845742 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0414. Min Act: -0.1700

Data Index: 270528 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 448654 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0256. Min Act: -0.1700

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1700

Data Index: 149317 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1699

Data Index: 1267648 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1700

Data Index: 1281266 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1700

Data Index: 1100526 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.1990. Min Range: -3.1990

Max Act: 3.0098. Min Act: -0.1700

Data Index: 307958 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.9940. Min Act: -0.1700

Data Index: 101772 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.9940. Min Act: -0.1700

Data Index: 877928 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.1990. Min Range: -3.1990

Max Act: 2.9940. Min Act: -0.1700

Data Index: 1117610 (C4 (Web Text))

Max Activating Token Index: 933