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

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

Neuron 1911 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1196156 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.5261. Min Act: -0.1700

Data Index: 918669 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.5105. Min Act: -0.1700

Data Index: 105944 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1192487 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.5105. Min Act: -0.1700

Data Index: 1132519 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1217821 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4791. Min Act: -0.1700

Data Index: 354453 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4791. Min Act: -0.1700

Data Index: 771606 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4948. Min Act: -0.1700

Data Index: 761304 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4791. Min Act: -0.1700

Data Index: 562039 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1222315 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4635. Min Act: -0.1700

Data Index: 644389 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4478. Min Act: -0.1700

Data Index: 941390 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1331129 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4478. Min Act: -0.1700

Data Index: 1196800 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4478. Min Act: -0.1700

Data Index: 213823 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4478. Min Act: -0.1700

Data Index: 56372 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4321. Min Act: -0.1700

Data Index: 317311 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4321. Min Act: -0.1700

Data Index: 790257 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.5418. Min Range: -3.5418

Max Act: 3.4164. Min Act: -0.1700

Data Index: 494958 (C4 (Web Text))

Max Activating Token Index: 990