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

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

Neuron 432 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.7473. Min Act: -0.1700

Data Index: 1224427 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.6534. Min Act: -0.1700

Data Index: 373778 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.6221. Min Act: -0.1700

Data Index: 1143486 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.5438. Min Act: -0.1700

Data Index: 1227747 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.5282. Min Act: -0.1700

Data Index: 634715 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4655. Min Act: -0.1700

Data Index: 1625998 (Python Code)

Max Activating Token Index: 524

Text #6

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4655. Min Act: -0.1700

Data Index: 826287 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4655. Min Act: -0.1700

Data Index: 176714 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4185. Min Act: -0.1700

Data Index: 96652 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4028. Min Act: -0.1700

Data Index: 76702 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4341. Min Act: -0.1700

Data Index: 222652 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3871. Min Act: -0.1700

Data Index: 242405 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4498. Min Act: -0.1700

Data Index: 718432 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4185. Min Act: -0.1700

Data Index: 1304099 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.4185. Min Act: -0.1700

Data Index: 1272691 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3714. Min Act: -0.1700

Data Index: 910555 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3243. Min Act: -0.1700

Data Index: 130673 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3871. Min Act: -0.1700

Data Index: 181000 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3714. Min Act: -0.1700

Data Index: 1221786 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 3.7473. Min Range: -3.7473

Max Act: 3.3871. Min Act: -0.1700

Data Index: 1093636 (C4 (Web Text))

Max Activating Token Index: 685