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

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

Neuron 922 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: 3.4720. Min Range: -3.4720

Max Act: 3.4720. Min Act: -0.1700

Data Index: 940820 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.4715. Min Act: -0.1700

Data Index: 11527 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.4202. Min Act: -0.1700

Data Index: 595343 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3966. Min Act: -0.1700

Data Index: 937999 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3880. Min Act: -0.1700

Data Index: 827702 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3820. Min Act: -0.1700

Data Index: 1053904 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3962. Min Act: -0.1700

Data Index: 709893 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3523. Min Act: -0.1700

Data Index: 422217 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3261. Min Act: -0.1700

Data Index: 1186383 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3415. Min Act: -0.1700

Data Index: 419037 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3295. Min Act: -0.1700

Data Index: 244744 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3296. Min Act: -0.1700

Data Index: 972348 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3361. Min Act: -0.1700

Data Index: 781983 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2977. Min Act: -0.1700

Data Index: 548606 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3223. Min Act: -0.1700

Data Index: 364873 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3159. Min Act: -0.1700

Data Index: 135926 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3131. Min Act: -0.1700

Data Index: 868326 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3027. Min Act: -0.1700

Data Index: 1087779 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.3022. Min Act: -0.1700

Data Index: 425794 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.4720. Min Range: -3.4720

Max Act: 3.2944. Min Act: -0.1700

Data Index: 667245 (C4 (Web Text))

Max Activating Token Index: 73