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

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

Neuron 609 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: 5.6183. Min Range: -5.6183

Max Act: 5.6183. Min Act: -0.1700

Data Index: 625623 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.4308. Min Act: -0.1700

Data Index: 367365 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.3996. Min Act: -0.1700

Data Index: 1148273 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.3371. Min Act: -0.1700

Data Index: 445517 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.2433. Min Act: -0.1700

Data Index: 32237 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1808. Min Act: -0.1700

Data Index: 1350307 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.2121. Min Act: -0.1700

Data Index: 1281499 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 69300 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 334616 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 31803 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 1228620 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.0871. Min Act: -0.1700

Data Index: 523353 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.1183. Min Act: -0.1700

Data Index: 679340 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.0558. Min Act: -0.1700

Data Index: 439833 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.0558. Min Act: -0.1700

Data Index: 406680 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 5.6183. Min Range: -5.6183

Max Act: 4.9933. Min Act: -0.1700

Data Index: 922546 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 5.6183. Min Range: -5.6183

Max Act: 4.9933. Min Act: -0.1700

Data Index: 62556 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 5.6183. Min Range: -5.6183

Max Act: 4.9933. Min Act: -0.1700

Data Index: 569850 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.0558. Min Act: -0.1700

Data Index: 851044 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 5.6183. Min Range: -5.6183

Max Act: 5.0558. Min Act: -0.1700

Data Index: 670358 (C4 (Web Text))

Max Activating Token Index: 763