Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1040 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.2881. Min Act: -0.1700

Data Index: 1279485 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.2881. Min Act: -0.1700

Data Index: 821516 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1347427 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1148604 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1938. Min Act: -0.1700

Data Index: 534601 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1623. Min Act: -0.1700

Data Index: 1172213 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1308. Min Act: -0.1700

Data Index: 365883 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0993. Min Act: -0.1700

Data Index: 612159 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1308. Min Act: -0.1700

Data Index: 424124 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1308. Min Act: -0.1700

Data Index: 921394 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.1308. Min Act: -0.1700

Data Index: 916871 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1167802 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0993. Min Act: -0.1700

Data Index: 134931 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0993. Min Act: -0.1700

Data Index: 870664 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0993. Min Act: -0.1700

Data Index: 593656 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 840634 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 719735 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 464364 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 237681 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 3.2881. Min Range: -3.2881

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1039580 (C4 (Web Text))

Max Activating Token Index: 553