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

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

Neuron 156 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: 3.2367. Min Range: -3.2367

Max Act: 3.2367. Min Act: -0.1700

Data Index: 470180 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1921. Min Act: -0.1700

Data Index: 952932 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1408. Min Act: -0.1700

Data Index: 216315 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1384. Min Act: -0.1700

Data Index: 1144442 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1422. Min Act: -0.1700

Data Index: 672547 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1507. Min Act: -0.1700

Data Index: 931741 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1168. Min Act: -0.1700

Data Index: 686855 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1367. Min Act: -0.1700

Data Index: 1064023 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1271. Min Act: -0.1700

Data Index: 361063 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1233. Min Act: -0.1700

Data Index: 559002 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1142. Min Act: -0.1699

Data Index: 630267 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1210. Min Act: -0.1700

Data Index: 1299185 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1264. Min Act: -0.1700

Data Index: 848803 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1170. Min Act: -0.1700

Data Index: 798742 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.1033. Min Act: -0.1700

Data Index: 967869 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1223667 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0935. Min Act: -0.1700

Data Index: 806721 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0664. Min Act: -0.1700

Data Index: 805921 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0797. Min Act: -0.1700

Data Index: 847202 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 3.2367. Min Range: -3.2367

Max Act: 3.0878. Min Act: -0.1700

Data Index: 89526 (C4 (Web Text))

Max Activating Token Index: 754