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

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

Neuron 1806 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: 3.4031. Min Range: -3.4031

Max Act: 3.4031. Min Act: -0.1700

Data Index: 214306 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.3678. Min Act: -0.1700

Data Index: 1345678 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.3396. Min Act: -0.1700

Data Index: 870597 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2944. Min Act: -0.1696

Data Index: 198303 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.3180. Min Act: -0.1574

Data Index: 1257646 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1341404 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2550. Min Act: -0.1700

Data Index: 1186879 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2658. Min Act: -0.1700

Data Index: 656991 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2496. Min Act: -0.1700

Data Index: 898998 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2199. Min Act: -0.1700

Data Index: 837076 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.2086. Min Act: -0.1700

Data Index: 518464 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1689. Min Act: -0.1700

Data Index: 602096 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1765. Min Act: -0.1700

Data Index: 456467 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1646. Min Act: -0.1700

Data Index: 194874 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1764. Min Act: -0.1700

Data Index: 101694 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1628. Min Act: -0.1700

Data Index: 1104608 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1359. Min Act: -0.1700

Data Index: 691399 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1261. Min Act: -0.1700

Data Index: 1022860 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1241. Min Act: -0.1700

Data Index: 695409 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.4031. Min Range: -3.4031

Max Act: 3.1286. Min Act: -0.1698

Data Index: 40133 (C4 (Web Text))

Max Activating Token Index: 489