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

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

Neuron 903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.4303. Min Act: -0.1700

Data Index: 1256794 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.2428. Min Act: -0.1700

Data Index: 839394 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.2740. Min Act: -0.1700

Data Index: 26100 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1178. Min Act: -0.1700

Data Index: 383806 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1490. Min Act: -0.1700

Data Index: 1134530 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.1178. Min Act: -0.1700

Data Index: 663858 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0865. Min Act: -0.1700

Data Index: 202351 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0240. Min Act: -0.1700

Data Index: 158316 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0865. Min Act: -0.1700

Data Index: 935418 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0553. Min Act: -0.1700

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0553. Min Act: -0.1700

Data Index: 173652 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9928. Min Act: -0.1700

Data Index: 303411 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9928. Min Act: -0.1700

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0240. Min Act: -0.1700

Data Index: 109393 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0553. Min Act: -0.1700

Data Index: 1324090 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9615. Min Act: -0.1700

Data Index: 1128086 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0240. Min Act: -0.1700

Data Index: 957873 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 5.4303. Min Range: -5.4303

Max Act: 5.0240. Min Act: -0.1700

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9615. Min Act: -0.1700

Data Index: 956133 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 5.4303. Min Range: -5.4303

Max Act: 4.9928. Min Act: -0.1700

Data Index: 869583 (C4 (Web Text))

Max Activating Token Index: 676