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

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

Neuron 91 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: 3.4240. Min Range: -3.4240

Max Act: 3.4240. Min Act: -0.1700

Data Index: 242741 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.3917. Min Act: -0.1512

Data Index: 904969 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.3173. Min Act: -0.1700

Data Index: 761840 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2850. Min Act: -0.1700

Data Index: 823195 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2789. Min Act: -0.1700

Data Index: 125011 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2474. Min Act: -0.1699

Data Index: 897297 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2611. Min Act: -0.1700

Data Index: 1015174 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2439. Min Act: -0.1700

Data Index: 255907 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2405. Min Act: -0.1700

Data Index: 18970 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2145. Min Act: -0.1700

Data Index: 781670 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.2031. Min Act: -0.1700

Data Index: 1085412 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1687. Min Act: -0.1700

Data Index: 53428 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1773. Min Act: -0.1700

Data Index: 876065 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1797. Min Act: -0.1675

Data Index: 943490 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1689. Min Act: 0.0806

Data Index: 1399735 (Python Code)

Max Activating Token Index: 1014

Text #15

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1541. Min Act: -0.1697

Data Index: 38111 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1641. Min Act: -0.1700

Data Index: 100075 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1586. Min Act: -0.1700

Data Index: 435113 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1415. Min Act: -0.1700

Data Index: 161269 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.4240. Min Range: -3.4240

Max Act: 3.1509. Min Act: -0.1700

Data Index: 744556 (C4 (Web Text))

Max Activating Token Index: 26