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

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

Neuron 238 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: 3.3411. Min Range: -3.3411

Max Act: 3.3411. Min Act: -0.1700

Data Index: 340492 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2940. Min Act: -0.1700

Data Index: 1169989 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2468. Min Act: -0.1700

Data Index: 98894 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2154. Min Act: -0.1700

Data Index: 1237690 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1131868 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2154. Min Act: -0.1700

Data Index: 223903 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2154. Min Act: -0.1700

Data Index: 1259594 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2154. Min Act: -0.1700

Data Index: 94846 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1996. Min Act: -0.1700

Data Index: 1305626 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1839. Min Act: -0.1700

Data Index: 565641 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1996. Min Act: -0.1700

Data Index: 112821 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1839. Min Act: -0.1700

Data Index: 694620 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1839. Min Act: -0.1700

Data Index: 453729 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1682. Min Act: -0.1700

Data Index: 410595 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1682. Min Act: -0.1700

Data Index: 1300917 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1839. Min Act: -0.1700

Data Index: 219034 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1996. Min Act: -0.1700

Data Index: 203536 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1682. Min Act: -0.1700

Data Index: 1067749 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1524. Min Act: -0.1700

Data Index: 1541966 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1682. Min Act: -0.1700

Data Index: 223939 (C4 (Web Text))

Max Activating Token Index: 597