Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 488 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.5924. Min Act: -0.1700

Data Index: 983302 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.5444. Min Act: -0.1700

Data Index: 863573 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.5213. Min Act: -0.1700

Data Index: 785577 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.4606. Min Act: -0.1700

Data Index: 547111 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.4364. Min Act: -0.1700

Data Index: 1068410 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3949. Min Act: -0.1700

Data Index: 752430 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3691. Min Act: -0.1700

Data Index: 94472 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3521. Min Act: -0.1699

Data Index: 614223 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3282. Min Act: -0.1700

Data Index: 237736 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3159. Min Act: -0.1700

Data Index: 223589 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.3139. Min Act: -0.1700

Data Index: 108564 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2850. Min Act: -0.1667

Data Index: 895107 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1407397 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2694. Min Act: -0.1700

Data Index: 563119 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2521. Min Act: -0.1700

Data Index: 992486 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2488. Min Act: -0.1700

Data Index: 844173 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1191732 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2524. Min Act: -0.1700

Data Index: 1244439 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2509. Min Act: -0.1700

Data Index: 753021 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 3.5924. Min Range: -3.5924

Max Act: 3.2359. Min Act: -0.1682

Data Index: 922967 (C4 (Web Text))

Max Activating Token Index: 242