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

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

Neuron 216 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.5162. Min Act: -0.1700

Data Index: 555422 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.3912. Min Act: -0.1700

Data Index: 117254 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2662. Min Act: -0.1700

Data Index: 962076 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2349. Min Act: -0.1700

Data Index: 1062205 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2037. Min Act: -0.1700

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2349. Min Act: -0.1700

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2037. Min Act: -0.1700

Data Index: 335823 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.1412. Min Act: -0.1699

Data Index: 1185211 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.1099. Min Act: -0.1700

Data Index: 4416 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.2037. Min Act: -0.1700

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.1099. Min Act: -0.1700

Data Index: 266729 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.0474. Min Act: -0.1700

Data Index: 427852 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 5.5162. Min Range: -5.5162

Max Act: 5.0162. Min Act: -0.1700

Data Index: 641930 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9849. Min Act: -0.1700

Data Index: 963655 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9849. Min Act: -0.1700

Data Index: 913552 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9537. Min Act: -0.1700

Data Index: 572775 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9849. Min Act: -0.1700

Data Index: 824253 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9849. Min Act: -0.1700

Data Index: 1196912 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.9849. Min Act: -0.1700

Data Index: 902288 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 5.5162. Min Range: -5.5162

Max Act: 4.8912. Min Act: -0.1700

Data Index: 278368 (C4 (Web Text))

Max Activating Token Index: 1018