Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1315 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3402. Min Range: -5.3402

Max Act: 5.3402. Min Act: -0.1700

Data Index: 3505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.7777. Min Act: -0.1700

Data Index: 154072 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5902. Min Act: -0.1700

Data Index: 675827 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5590. Min Act: -0.1700

Data Index: 1089758 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.6527. Min Act: -0.1700

Data Index: 1306533 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5590. Min Act: -0.1700

Data Index: 1011522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5590. Min Act: -0.1700

Data Index: 535057 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5590. Min Act: -0.1700

Data Index: 724997 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 661553 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 40436 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 1285632 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 990123 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 1069217 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.5277. Min Act: -0.1700

Data Index: 719606 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4964. Min Act: -0.1700

Data Index: 1313224 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4964. Min Act: -0.1700

Data Index: 492091 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4652. Min Act: -0.1700

Data Index: 930469 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4339. Min Act: -0.1700

Data Index: 218657 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4964. Min Act: -0.1700

Data Index: 816878 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 5.3402. Min Range: -5.3402

Max Act: 4.4964. Min Act: -0.1700

Data Index: 291857 (C4 (Web Text))

Max Activating Token Index: 950