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

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

Neuron 722 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: 5.4277. Min Range: -5.4277

Max Act: 5.4277. Min Act: -0.1700

Data Index: 1077099 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.3964. Min Act: -0.1700

Data Index: 723194 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.2714. Min Act: -0.1700

Data Index: 102339 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.3652. Min Act: -0.1700

Data Index: 935202 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.2089. Min Act: -0.1700

Data Index: 689323 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1159069 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1464. Min Act: -0.1699

Data Index: 742572 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0839. Min Act: -0.1700

Data Index: 1298328 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1464. Min Act: -0.1700

Data Index: 593744 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1464. Min Act: -0.1700

Data Index: 1152116 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0839. Min Act: -0.1700

Data Index: 645596 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1316100 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0839. Min Act: -0.1700

Data Index: 637904 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1777. Min Act: -0.1700

Data Index: 472162 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0527. Min Act: -0.1699

Data Index: 561029 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 5.4277. Min Range: -5.4277

Max Act: 4.9902. Min Act: -0.1700

Data Index: 1038332 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0839. Min Act: -0.1700

Data Index: 1185315 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.1777. Min Act: -0.1700

Data Index: 1246281 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 5.4277. Min Range: -5.4277

Max Act: 4.9902. Min Act: -0.1700

Data Index: 477932 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 5.4277. Min Range: -5.4277

Max Act: 5.0839. Min Act: -0.1700

Data Index: 1104494 (C4 (Web Text))

Max Activating Token Index: 317