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

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

Neuron 805 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: 2.9674. Min Range: -2.9674

Max Act: 2.9674. Min Act: -0.1700

Data Index: 752348 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.9187. Min Act: -0.1700

Data Index: 1007882 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.9259. Min Act: -0.1700

Data Index: 43166 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.9083. Min Act: -0.1700

Data Index: 685244 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.9163. Min Act: -0.1700

Data Index: 553101 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8946. Min Act: -0.1700

Data Index: 1351749 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8763. Min Act: -0.1700

Data Index: 825313 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8606. Min Act: -0.1700

Data Index: 996939 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8565. Min Act: -0.1700

Data Index: 944173 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8544. Min Act: -0.1700

Data Index: 71096 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8424. Min Act: -0.1700

Data Index: 524038 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8460. Min Act: -0.1700

Data Index: 907898 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8262. Min Act: -0.1700

Data Index: 82918 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8331. Min Act: -0.1700

Data Index: 966487 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8380. Min Act: -0.1700

Data Index: 1119165 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8185. Min Act: -0.1700

Data Index: 269596 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8150. Min Act: -0.1698

Data Index: 575927 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8082. Min Act: -0.1700

Data Index: 1098233 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8191. Min Act: -0.1699

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 2.9674. Min Range: -2.9674

Max Act: 2.8135. Min Act: -0.1700

Data Index: 47214 (C4 (Web Text))

Max Activating Token Index: 580