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

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

Neuron 1118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4909. Min Act: -0.1700

Data Index: 512421 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4596. Min Act: -0.1700

Data Index: 1172622 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4596. Min Act: -0.1700

Data Index: 619274 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4596. Min Act: -0.1700

Data Index: 808459 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4439. Min Act: -0.1700

Data Index: 1007587 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4282. Min Act: -0.1700

Data Index: 1193210 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3969. Min Act: -0.1700

Data Index: 933127 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4126. Min Act: -0.1700

Data Index: 762382 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.4126. Min Act: -0.1700

Data Index: 615744 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3655. Min Act: -0.1700

Data Index: 915026 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3655. Min Act: -0.1700

Data Index: 1151972 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3812. Min Act: -0.1700

Data Index: 360677 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3655. Min Act: -0.1700

Data Index: 244873 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3498. Min Act: -0.1700

Data Index: 1224912 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3498. Min Act: -0.1700

Data Index: 116918 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3812. Min Act: -0.1700

Data Index: 586831 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3184. Min Act: -0.1700

Data Index: 846306 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3498. Min Act: -0.1700

Data Index: 922296 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.3341. Min Act: -0.1700

Data Index: 340368 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 3.4909. Min Range: -3.4909

Max Act: 3.2870. Min Act: -0.1700

Data Index: 397088 (C4 (Web Text))

Max Activating Token Index: 545