Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 692 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.8921. Min Act: -0.1700

Data Index: 1012794 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.9188. Min Act: -0.1700

Data Index: 887930 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.8825. Min Act: -0.1700

Data Index: 1472573 (Python Code)

Max Activating Token Index: 372

Text #3

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.8805. Min Act: -0.1700

Data Index: 30082 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.8469. Min Act: -0.1699

Data Index: 1071763 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.8083. Min Act: -0.1700

Data Index: 70426 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7846. Min Act: -0.1700

Data Index: 1655194 (Python Code)

Max Activating Token Index: 848

Text #7

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7795. Min Act: -0.1700

Data Index: 614356 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7727. Min Act: -0.1700

Data Index: 980265 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7664. Min Act: -0.1700

Data Index: 908421 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7605. Min Act: -0.1700

Data Index: 671806 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7281. Min Act: -0.1700

Data Index: 1489309 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7554. Min Act: -0.1700

Data Index: 1559528 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7449. Min Act: -0.1700

Data Index: 156112 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7198. Min Act: -0.1700

Data Index: 1400763 (Python Code)

Max Activating Token Index: 627

Text #15

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7421. Min Act: -0.1700

Data Index: 857910 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7323. Min Act: -0.1700

Data Index: 1217925 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7394. Min Act: -0.1700

Data Index: 629000 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7462. Min Act: -0.1700

Data Index: 962305 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 2.9188. Min Range: -2.9188

Max Act: 2.7127. Min Act: -0.1700

Data Index: 1359974 (Python Code)

Max Activating Token Index: 718