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

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

Neuron 33 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: 5.1001. Min Range: -5.1001

Max Act: 5.1001. Min Act: -0.1700

Data Index: 726832 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 5.1001. Min Range: -5.1001

Max Act: 5.1001. Min Act: -0.1700

Data Index: 831245 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.9439. Min Act: -0.1700

Data Index: 364806 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.9126. Min Act: -0.1700

Data Index: 747373 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.9126. Min Act: -0.1700

Data Index: 902462 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 477513 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8501. Min Act: -0.1700

Data Index: 959734 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 434714 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8814. Min Act: -0.1700

Data Index: 50659 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1265030 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 195039 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 107232 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 693929 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.8189. Min Act: -0.1700

Data Index: 1187317 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7564. Min Act: -0.1700

Data Index: 1046561 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7876. Min Act: -0.1700

Data Index: 431975 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7251. Min Act: -0.1700

Data Index: 627253 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7876. Min Act: -0.1700

Data Index: 138043 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7251. Min Act: -0.1700

Data Index: 950396 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 5.1001. Min Range: -5.1001

Max Act: 4.7251. Min Act: -0.1700

Data Index: 918204 (C4 (Web Text))

Max Activating Token Index: 41