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

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

Neuron 1470 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.8033. Min Act: -0.1700

Data Index: 1358272 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.7721. Min Act: -0.1700

Data Index: 765459 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6938. Min Act: -0.1699

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.7095. Min Act: -0.1700

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.7095. Min Act: -0.1700

Data Index: 1127190 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6782. Min Act: -0.1700

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.7095. Min Act: -0.1700

Data Index: 293208 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6938. Min Act: -0.1700

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6938. Min Act: -0.1700

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6938. Min Act: -0.1700

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1036748 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.5999. Min Act: -0.1700

Data Index: 1026316 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6469. Min Act: -0.1700

Data Index: 1022409 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6469. Min Act: -0.1700

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6156. Min Act: -0.1700

Data Index: 871036 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.5999. Min Act: -0.1700

Data Index: 287974 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6312. Min Act: -0.1700

Data Index: 347647 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6312. Min Act: -0.1700

Data Index: 783106 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6156. Min Act: -0.1700

Data Index: 761140 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.8033. Min Range: -3.8033

Max Act: 3.6156. Min Act: -0.1700

Data Index: 408484 (C4 (Web Text))

Max Activating Token Index: 139