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

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

Neuron 1780 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: 3.4675. Min Range: -3.4675

Max Act: 3.4675. Min Act: -0.1700

Data Index: 1186580 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.4192. Min Act: -0.1700

Data Index: 69159 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3543. Min Act: -0.1700

Data Index: 477446 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3525. Min Act: -0.1700

Data Index: 173057 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3469. Min Act: -0.1700

Data Index: 542427 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3230. Min Act: -0.1700

Data Index: 596336 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3183. Min Act: -0.1700

Data Index: 1298143 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2593. Min Act: -0.1700

Data Index: 1341300 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.3141. Min Act: -0.1700

Data Index: 225917 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2788. Min Act: -0.1700

Data Index: 127670 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2741. Min Act: -0.1700

Data Index: 197690 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2901. Min Act: -0.1700

Data Index: 238104 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2503. Min Act: -0.1700

Data Index: 83078 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2459. Min Act: -0.1700

Data Index: 861849 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2837. Min Act: -0.1700

Data Index: 707126 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2488. Min Act: -0.1700

Data Index: 314530 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2617. Min Act: -0.1700

Data Index: 113854 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2454. Min Act: -0.1700

Data Index: 521268 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2500. Min Act: -0.1700

Data Index: 500110 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 3.4675. Min Range: -3.4675

Max Act: 3.2439. Min Act: -0.1700

Data Index: 678942 (C4 (Web Text))

Max Activating Token Index: 115