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

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

Neuron 1919 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.7313. Min Act: -0.1700

Data Index: 63401 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.7156. Min Act: -0.1700

Data Index: 756901 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6843. Min Act: -0.1700

Data Index: 906775 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6530. Min Act: -0.1700

Data Index: 308064 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6687. Min Act: -0.1700

Data Index: 940128 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6530. Min Act: -0.1700

Data Index: 255277 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6374. Min Act: -0.1700

Data Index: 822377 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6687. Min Act: -0.1700

Data Index: 137912 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6374. Min Act: -0.1700

Data Index: 232396 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6217. Min Act: -0.1700

Data Index: 539006 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1159802 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6217. Min Act: -0.1700

Data Index: 697520 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6217. Min Act: -0.1700

Data Index: 1182568 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6217. Min Act: -0.1700

Data Index: 594645 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.5904. Min Act: -0.1700

Data Index: 997804 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6061. Min Act: -0.1700

Data Index: 605566 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.6061. Min Act: -0.1700

Data Index: 764424 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.5904. Min Act: -0.1700

Data Index: 995814 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.5904. Min Act: -0.1700

Data Index: 517670 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 3.7313. Min Range: -3.7313

Max Act: 3.5904. Min Act: -0.1700

Data Index: 615974 (C4 (Web Text))

Max Activating Token Index: 985