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

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

Neuron 1232 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: 3.6508. Min Range: -3.6508

Max Act: 3.6508. Min Act: -0.1700

Data Index: 660846 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6258. Min Act: -0.1700

Data Index: 873099 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.6091. Min Act: -0.1700

Data Index: 521248 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5468. Min Act: -0.1700

Data Index: 472026 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5560. Min Act: -0.1700

Data Index: 1100814 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5433. Min Act: -0.1700

Data Index: 725172 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5461. Min Act: -0.1700

Data Index: 996747 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5507. Min Act: -0.1700

Data Index: 614228 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5274. Min Act: -0.1700

Data Index: 464274 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5265. Min Act: -0.1700

Data Index: 7127 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5228. Min Act: -0.1700

Data Index: 858970 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.5168. Min Act: -0.1700

Data Index: 829546 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4890. Min Act: -0.1700

Data Index: 846827 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4936. Min Act: -0.1700

Data Index: 4570 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4769. Min Act: -0.1700

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4759. Min Act: -0.1700

Data Index: 838451 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4638. Min Act: -0.1700

Data Index: 1330456 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4671. Min Act: -0.1700

Data Index: 15340 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4814. Min Act: -0.1700

Data Index: 1037065 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 3.6508. Min Range: -3.6508

Max Act: 3.4729. Min Act: -0.1700

Data Index: 920643 (C4 (Web Text))

Max Activating Token Index: 563