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

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

Neuron 316 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: 2.9272. Min Range: -2.9272

Max Act: 2.9272. Min Act: -0.1700

Data Index: 1509824 (Python Code)

Max Activating Token Index: 498

Text #1

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.8669. Min Act: -0.1700

Data Index: 1559568 (Python Code)

Max Activating Token Index: 36

Text #2

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7854. Min Act: -0.1700

Data Index: 58542 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.8038. Min Act: -0.1700

Data Index: 1368506 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7887. Min Act: -0.1700

Data Index: 1302646 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7633. Min Act: -0.1700

Data Index: 1373402 (Python Code)

Max Activating Token Index: 105

Text #6

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7553. Min Act: -0.1700

Data Index: 1117336 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7604. Min Act: -0.1700

Data Index: 180897 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7441. Min Act: -0.1700

Data Index: 1484214 (Python Code)

Max Activating Token Index: 998

Text #9

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7337. Min Act: -0.1700

Data Index: 1419650 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7311. Min Act: -0.1700

Data Index: 1123113 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7027. Min Act: -0.1700

Data Index: 1229957 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.7036. Min Act: -0.1700

Data Index: 1000433 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6866. Min Act: -0.1700

Data Index: 1475000 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6749. Min Act: -0.1700

Data Index: 238262 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6847. Min Act: -0.1700

Data Index: 791226 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6884. Min Act: -0.1700

Data Index: 240971 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6657. Min Act: -0.1700

Data Index: 1370476 (Python Code)

Max Activating Token Index: 842

Text #18

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6644. Min Act: -0.1700

Data Index: 1549771 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 2.9272. Min Range: -2.9272

Max Act: 2.6630. Min Act: -0.1700

Data Index: 578776 (C4 (Web Text))

Max Activating Token Index: 405