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

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

Neuron 450 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1316. Min Range: -3.1316

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1250173 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.8627. Min Act: -0.1700

Data Index: 665673 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.8309. Min Act: -0.1700

Data Index: 730603 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7991. Min Act: -0.1700

Data Index: 86784 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7991. Min Act: -0.1700

Data Index: 168049 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7991. Min Act: -0.1700

Data Index: 239991 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7991. Min Act: -0.1700

Data Index: 298037 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7513. Min Act: -0.1700

Data Index: 898758 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7193. Min Act: -0.1700

Data Index: 680376 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7353. Min Act: -0.1700

Data Index: 1337075 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7033. Min Act: -0.1700

Data Index: 511605 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7353. Min Act: -0.1700

Data Index: 785854 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7033. Min Act: -0.1700

Data Index: 1049800 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6873. Min Act: -0.1700

Data Index: 435241 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6873. Min Act: -0.1700

Data Index: 380058 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.7033. Min Act: -0.1700

Data Index: 1053485 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6873. Min Act: -0.1700

Data Index: 115589 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6713. Min Act: -0.1700

Data Index: 1484279 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6553. Min Act: -0.1700

Data Index: 1565627 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 3.1316. Min Range: -3.1316

Max Act: 2.6713. Min Act: -0.1700

Data Index: 627103 (C4 (Web Text))

Max Activating Token Index: 632