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

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

Neuron 353 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: 5.1635. Min Range: -5.1635

Max Act: 5.1635. Min Act: -0.1700

Data Index: 905823 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.7573. Min Act: -0.1700

Data Index: 876181 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.7260. Min Act: -0.1700

Data Index: 66510 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.6010. Min Act: -0.1700

Data Index: 1163285 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.6010. Min Act: -0.1700

Data Index: 953228 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.6010. Min Act: -0.1700

Data Index: 1281931 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 847025 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.6010. Min Act: -0.1700

Data Index: 874240 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 133436 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5385. Min Act: -0.1700

Data Index: 236908 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.4760. Min Act: -0.1700

Data Index: 858283 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 548396 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 268768 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 224979 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.4760. Min Act: -0.1700

Data Index: 1081705 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.4760. Min Act: -0.1699

Data Index: 17505 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.5073. Min Act: -0.1700

Data Index: 545440 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.6010. Min Act: -0.1700

Data Index: 672617 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.4760. Min Act: -0.1700

Data Index: 1084879 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 5.1635. Min Range: -5.1635

Max Act: 4.4760. Min Act: -0.1700

Data Index: 902521 (C4 (Web Text))

Max Activating Token Index: 857