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

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

Neuron 481 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: 3.8165. Min Range: -3.8165

Max Act: 3.8165. Min Act: -0.1698

Data Index: 415965 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6364. Min Act: -0.1700

Data Index: 864549 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.6115. Min Act: -0.1700

Data Index: 1011777 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5894. Min Act: -0.1699

Data Index: 583091 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5906. Min Act: -0.1700

Data Index: 836757 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5722. Min Act: -0.1700

Data Index: 1192819 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5649. Min Act: -0.1700

Data Index: 6244 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5214. Min Act: -0.1700

Data Index: 629148 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.5192. Min Act: -0.1700

Data Index: 1092104 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4902. Min Act: -0.1700

Data Index: 621601 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4976. Min Act: -0.1700

Data Index: 664315 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4681. Min Act: -0.1700

Data Index: 1297767 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4715. Min Act: -0.1700

Data Index: 962703 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4663. Min Act: -0.1700

Data Index: 18387 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4581. Min Act: -0.1700

Data Index: 1294592 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4276. Min Act: -0.1676

Data Index: 1251551 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4157. Min Act: -0.1700

Data Index: 515225 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4497. Min Act: -0.1699

Data Index: 899339 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4410. Min Act: -0.1700

Data Index: 784307 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 3.8165. Min Range: -3.8165

Max Act: 3.4507. Min Act: -0.1700

Data Index: 172401 (C4 (Web Text))

Max Activating Token Index: 18