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

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

Neuron 663 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: 5.8155. Min Range: -5.8155

Max Act: 5.7842. Min Act: -0.1700

Data Index: 138678 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.8155. Min Act: -0.1700

Data Index: 466182 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6905. Min Act: -0.1700

Data Index: 928106 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6905. Min Act: -0.1700

Data Index: 5374 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6592. Min Act: -0.1700

Data Index: 1220365 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6905. Min Act: -0.1700

Data Index: 613286 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6280. Min Act: -0.1700

Data Index: 1234056 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.6280. Min Act: -0.1700

Data Index: 589005 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.5342. Min Act: -0.1700

Data Index: 709417 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4717. Min Act: -0.1700

Data Index: 129668 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.5030. Min Act: -0.1700

Data Index: 259988 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4717. Min Act: -0.1700

Data Index: 955167 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4092. Min Act: -0.1700

Data Index: 772833 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.5030. Min Act: -0.1700

Data Index: 675587 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.5342. Min Act: -0.1700

Data Index: 368845 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4405. Min Act: -0.1700

Data Index: 175661 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.5030. Min Act: -0.1700

Data Index: 1292686 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4405. Min Act: -0.1700

Data Index: 96824 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4405. Min Act: -0.1700

Data Index: 735999 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 5.8155. Min Range: -5.8155

Max Act: 5.4405. Min Act: -0.1700

Data Index: 355039 (C4 (Web Text))

Max Activating Token Index: 1021