Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1119 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 12.2822. Min Range: -12.2822

Max Act: 12.2822. Min Act: -0.1700

Data Index: 125337 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.9697. Min Act: -0.1700

Data Index: 55036 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.7822. Min Act: -0.1698

Data Index: 424984 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.7197. Min Act: -0.1700

Data Index: 436458 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.2197. Min Act: -0.1700

Data Index: 670829 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.2822. Min Act: -0.1699

Data Index: 395036 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.2197. Min Act: -0.1700

Data Index: 710307 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.2197. Min Act: -0.1700

Data Index: 1020201 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.2197. Min Act: -0.1700

Data Index: 1165803 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.1572. Min Act: -0.1700

Data Index: 990018 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.1572. Min Act: -0.1365

Data Index: 1017869 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.0322. Min Act: -0.1700

Data Index: 1301404 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.9697. Min Act: -0.1700

Data Index: 1229681 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 12.2822. Min Range: -12.2822

Max Act: 11.0947. Min Act: -0.1700

Data Index: 190481 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.9697. Min Act: -0.1700

Data Index: 351735 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.8447. Min Act: -0.1700

Data Index: 185377 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.7822. Min Act: -0.1700

Data Index: 723423 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.8447. Min Act: -0.1700

Data Index: 1101965 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.8447. Min Act: -0.1700

Data Index: 733212 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 12.2822. Min Range: -12.2822

Max Act: 10.9072. Min Act: -0.1700

Data Index: 675289 (C4 (Web Text))

Max Activating Token Index: 550