Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1143 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.7175. Min Act: -0.1700

Data Index: 1277475 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.6236. Min Act: -0.1700

Data Index: 1288031 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.6862. Min Act: -0.1700

Data Index: 1154450 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.6236. Min Act: -0.1700

Data Index: 220241 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 1328110 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5923. Min Act: -0.1700

Data Index: 357028 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5923. Min Act: -0.1700

Data Index: 923413 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 1193302 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 646888 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 944881 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 855075 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 189629 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.4983. Min Act: -0.1700

Data Index: 998349 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 750070 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 902899 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 1188323 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 111620 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5610. Min Act: -0.1700

Data Index: 536003 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.5296. Min Act: -0.1700

Data Index: 185229 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.7175. Min Range: -3.7175

Max Act: 3.4983. Min Act: -0.1700

Data Index: 176645 (C4 (Web Text))

Max Activating Token Index: 63