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

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

Neuron 1607 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: 3.4459. Min Range: -3.4459

Max Act: 3.4459. Min Act: -0.1700

Data Index: 1547132 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4341. Min Act: -0.1700

Data Index: 1576282 (Python Code)

Max Activating Token Index: 364

Text #2

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4179. Min Act: -0.1700

Data Index: 305579 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.4229. Min Act: -0.1700

Data Index: 1552033 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3852. Min Act: -0.1700

Data Index: 1268170 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3737. Min Act: -0.1700

Data Index: 1604451 (Python Code)

Max Activating Token Index: 199

Text #6

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3618. Min Act: -0.1700

Data Index: 422255 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3483. Min Act: -0.1700

Data Index: 33996 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3142. Min Act: -0.1700

Data Index: 140810 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1650508 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3163. Min Act: -0.1700

Data Index: 1518482 (Python Code)

Max Activating Token Index: 951

Text #11

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3123. Min Act: -0.1700

Data Index: 1505494 (Python Code)

Max Activating Token Index: 844

Text #12

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3024. Min Act: -0.1700

Data Index: 823173 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.2705. Min Act: -0.1700

Data Index: 341255 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3028. Min Act: -0.1700

Data Index: 1395764 (Python Code)

Max Activating Token Index: 335

Text #15

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.2942. Min Act: -0.1700

Data Index: 1444123 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.2976. Min Act: -0.1700

Data Index: 1255807 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.2698. Min Act: -0.1700

Data Index: 1616954 (Python Code)

Max Activating Token Index: 539

Text #18

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.3009. Min Act: -0.1700

Data Index: 1440842 (Python Code)

Max Activating Token Index: 791

Text #19

Max Range: 3.4459. Min Range: -3.4459

Max Act: 3.2827. Min Act: -0.1700

Data Index: 324802 (C4 (Web Text))

Max Activating Token Index: 1010