Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1397 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2860. Min Act: -0.1700

Data Index: 210537 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2703. Min Act: -0.1700

Data Index: 181581 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2703. Min Act: -0.1700

Data Index: 728762 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2545. Min Act: -0.1700

Data Index: 522329 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1343946 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2545. Min Act: -0.1700

Data Index: 459025 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2545. Min Act: -0.1700

Data Index: 1002161 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 808740 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 769502 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 181835 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2231. Min Act: -0.1700

Data Index: 255940 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 659338 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2231. Min Act: -0.1700

Data Index: 697005 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 867884 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 1141948 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2231. Min Act: -0.1700

Data Index: 94077 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2074. Min Act: -0.1700

Data Index: 861574 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2231. Min Act: -0.1700

Data Index: 289114 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2388. Min Act: -0.1700

Data Index: 849954 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 3.2860. Min Range: -3.2860

Max Act: 3.2231. Min Act: -0.1700

Data Index: 516225 (C4 (Web Text))

Max Activating Token Index: 554