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

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

Neuron 736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.7155. Min Act: -0.1700

Data Index: 987229 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.7155. Min Act: -0.1700

Data Index: 1002121 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.6217. Min Act: -0.1700

Data Index: 533148 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.6217. Min Act: -0.1700

Data Index: 769901 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5905. Min Act: -0.1700

Data Index: 1033662 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5905. Min Act: -0.1700

Data Index: 1237368 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5280. Min Act: -0.1700

Data Index: 1320899 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5280. Min Act: -0.1700

Data Index: 1212002 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4655. Min Act: -0.1700

Data Index: 470517 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5280. Min Act: -0.1700

Data Index: 517430 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.5280. Min Act: -0.1700

Data Index: 784394 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4967. Min Act: -0.1700

Data Index: 89423 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4967. Min Act: -0.1700

Data Index: 907042 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4967. Min Act: -0.1700

Data Index: 1137742 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4655. Min Act: -0.1700

Data Index: 154291 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4655. Min Act: -0.1700

Data Index: 586644 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4967. Min Act: -0.1700

Data Index: 913211 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4655. Min Act: -0.1700

Data Index: 442369 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4342. Min Act: -0.1700

Data Index: 388336 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 5.7155. Min Range: -5.7155

Max Act: 5.4655. Min Act: -0.1700

Data Index: 195987 (C4 (Web Text))

Max Activating Token Index: 916