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

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

Neuron 141 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: 3.7332. Min Range: -3.7332

Max Act: 3.7332. Min Act: -0.1700

Data Index: 931899 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.6926. Min Act: -0.1700

Data Index: 1092583 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1303261 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5855. Min Act: -0.1700

Data Index: 1019345 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5681. Min Act: -0.1700

Data Index: 907311 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5485. Min Act: -0.1700

Data Index: 380714 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5276. Min Act: -0.1700

Data Index: 914707 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5377. Min Act: -0.1700

Data Index: 472790 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5007. Min Act: -0.1700

Data Index: 869044 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5239. Min Act: -0.1700

Data Index: 908268 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5474. Min Act: -0.1700

Data Index: 108188 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5230. Min Act: -0.1700

Data Index: 288462 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1121490 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5056. Min Act: -0.1700

Data Index: 935480 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.4924. Min Act: -0.1700

Data Index: 453682 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.5089. Min Act: -0.1700

Data Index: 1099256 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.4858. Min Act: -0.1700

Data Index: 383771 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.4714. Min Act: -0.1700

Data Index: 197238 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.4745. Min Act: -0.1700

Data Index: 808747 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 3.7332. Min Range: -3.7332

Max Act: 3.4516. Min Act: -0.1700

Data Index: 1176378 (C4 (Web Text))

Max Activating Token Index: 839