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

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

Neuron 44 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: 6.4090. Min Range: -6.4090

Max Act: 6.4090. Min Act: -0.1700

Data Index: 552497 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.3152. Min Act: -0.1700

Data Index: 1139882 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.1590. Min Act: -0.1700

Data Index: 966614 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.0965. Min Act: -0.1700

Data Index: 920473 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.1277. Min Act: -0.1700

Data Index: 991752 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.1277. Min Act: -0.1700

Data Index: 1077062 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.1277. Min Act: -0.1700

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9402. Min Act: -0.1700

Data Index: 929156 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.0027. Min Act: -0.1700

Data Index: 218211 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9715. Min Act: -0.1700

Data Index: 162377 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.0340. Min Act: -0.1700

Data Index: 507071 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.0340. Min Act: -0.1700

Data Index: 239374 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9402. Min Act: -0.1700

Data Index: 126724 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 6.4090. Min Range: -6.4090

Max Act: 6.0965. Min Act: -0.1700

Data Index: 1355317 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9715. Min Act: -0.1700

Data Index: 643412 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9090. Min Act: -0.1700

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9090. Min Act: -0.1700

Data Index: 486731 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9090. Min Act: -0.1700

Data Index: 1290420 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9715. Min Act: -0.1700

Data Index: 900802 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 6.4090. Min Range: -6.4090

Max Act: 5.9402. Min Act: -0.1700

Data Index: 105550 (C4 (Web Text))

Max Activating Token Index: 1013