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

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

Neuron 589 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.4380. Min Act: -0.1700

Data Index: 423611 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.4066. Min Act: -0.1700

Data Index: 939450 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.4066. Min Act: -0.1700

Data Index: 657340 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3752. Min Act: -0.1700

Data Index: 954647 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3752. Min Act: -0.1700

Data Index: 527296 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3752. Min Act: -0.1700

Data Index: 1093346 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3752. Min Act: -0.1700

Data Index: 285219 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3595. Min Act: -0.1700

Data Index: 900247 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3752. Min Act: -0.1700

Data Index: 240076 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3438. Min Act: -0.1700

Data Index: 59930 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3281. Min Act: -0.1700

Data Index: 390442 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.3124. Min Act: -0.1700

Data Index: 858140 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2967. Min Act: -0.1700

Data Index: 414043 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2967. Min Act: -0.1700

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2967. Min Act: -0.1700

Data Index: 36267 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2967. Min Act: -0.1700

Data Index: 930596 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2810. Min Act: -0.1700

Data Index: 217378 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2810. Min Act: -0.1700

Data Index: 466820 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2653. Min Act: -0.1700

Data Index: 998527 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.4380. Min Range: -3.4380

Max Act: 3.2967. Min Act: -0.1700

Data Index: 932794 (C4 (Web Text))

Max Activating Token Index: 301