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

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

Neuron 109 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: 8.2161. Min Range: -8.2161

Max Act: 8.2161. Min Act: -0.1700

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 8.2161. Min Range: -8.2161

Max Act: 8.0589. Min Act: -0.1700

Data Index: 742431 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.9404. Min Act: -0.1700

Data Index: 51667 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7794. Min Act: -0.1700

Data Index: 957323 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7754. Min Act: -0.1700

Data Index: 76815 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.8037. Min Act: -0.1699

Data Index: 367965 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7577. Min Act: -0.1700

Data Index: 1349289 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7559. Min Act: -0.1700

Data Index: 120361 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7096. Min Act: -0.1700

Data Index: 1162906 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6780. Min Act: -0.1700

Data Index: 1190268 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7477. Min Act: -0.1700

Data Index: 1289818 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.7330. Min Act: -0.1700

Data Index: 752059 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6564. Min Act: -0.1700

Data Index: 711846 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6520. Min Act: -0.1700

Data Index: 182574 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6842. Min Act: -0.1700

Data Index: 147101 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6370. Min Act: -0.1700

Data Index: 1050546 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6130. Min Act: -0.1700

Data Index: 635095 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6912. Min Act: -0.1700

Data Index: 1248848 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.6176. Min Act: -0.1700

Data Index: 402743 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 8.2161. Min Range: -8.2161

Max Act: 7.5318. Min Act: -0.1700

Data Index: 626186 (C4 (Web Text))

Max Activating Token Index: 343