Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1130 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.6431. Min Act: -0.1700

Data Index: 411777 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.6118. Min Act: -0.1700

Data Index: 893880 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.6118. Min Act: -0.1700

Data Index: 451282 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.5805. Min Act: -0.1700

Data Index: 735168 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.5805. Min Act: -0.1700

Data Index: 208194 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.5492. Min Act: -0.1700

Data Index: 490428 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4865. Min Act: -0.1700

Data Index: 440591 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4865. Min Act: -0.1700

Data Index: 822687 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4865. Min Act: -0.1700

Data Index: 1073898 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4865. Min Act: -0.1700

Data Index: 967171 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1224198 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4238. Min Act: -0.1700

Data Index: 1075137 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 669079 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 909999 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1186439 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4238. Min Act: -0.1700

Data Index: 454526 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 823575 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1053729 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.4238. Min Act: -0.1700

Data Index: 731265 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 3.6431. Min Range: -3.6431

Max Act: 3.3611. Min Act: -0.1700

Data Index: 1118904 (C4 (Web Text))

Max Activating Token Index: 80