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

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

Neuron 1215 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.3465. Min Act: -0.1700

Data Index: 1300248 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2527. Min Act: -0.1700

Data Index: 655618 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2840. Min Act: -0.1700

Data Index: 312672 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1197185 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2527. Min Act: -0.1700

Data Index: 543471 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2840. Min Act: -0.1700

Data Index: 53798 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2215. Min Act: -0.1700

Data Index: 1114363 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2527. Min Act: -0.1700

Data Index: 206948 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2215. Min Act: -0.1700

Data Index: 401506 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2215. Min Act: -0.1700

Data Index: 570935 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1902. Min Act: -0.1700

Data Index: 521772 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.2215. Min Act: -0.1700

Data Index: 180523 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1356496 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1283886 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1277. Min Act: -0.1700

Data Index: 667065 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1277. Min Act: -0.1700

Data Index: 222353 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1590. Min Act: -0.1700

Data Index: 532550 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1048304 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1590. Min Act: -0.1700

Data Index: 592515 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 5.3465. Min Range: -5.3465

Max Act: 5.1590. Min Act: -0.1700

Data Index: 1174503 (C4 (Web Text))

Max Activating Token Index: 436