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

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

Neuron 1359 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: 5.5768. Min Range: -5.5768

Max Act: 5.5768. Min Act: -0.1700

Data Index: 1550204 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.5768. Min Act: -0.1700

Data Index: 274722 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.5768. Min Act: -0.1700

Data Index: 1513714 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4205. Min Act: -0.1700

Data Index: 443772 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4830. Min Act: -0.1700

Data Index: 1541167 (Python Code)

Max Activating Token Index: 288

Text #5

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1644895 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4205. Min Act: -0.1700

Data Index: 109367 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4830. Min Act: -0.1700

Data Index: 34557 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4205. Min Act: -0.1700

Data Index: 1407430 (Python Code)

Max Activating Token Index: 470

Text #9

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.4205. Min Act: -0.1700

Data Index: 1597731 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3893. Min Act: -0.1700

Data Index: 1479009 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3893. Min Act: -0.1700

Data Index: 1649690 (Python Code)

Max Activating Token Index: 684

Text #12

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1416589 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1117183 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.2018. Min Act: -0.1700

Data Index: 468645 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1414104 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1449237 (Python Code)

Max Activating Token Index: 297

Text #17

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3580. Min Act: -0.1700

Data Index: 1622932 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3893. Min Act: -0.1700

Data Index: 1555521 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 5.5768. Min Range: -5.5768

Max Act: 5.3268. Min Act: -0.1700

Data Index: 1402444 (Python Code)

Max Activating Token Index: 527