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

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

Neuron 290 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2981. Min Act: -0.1700

Data Index: 275345 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.3293. Min Act: -0.1700

Data Index: 158389 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.3293. Min Act: -0.1700

Data Index: 192707 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2981. Min Act: -0.1700

Data Index: 509222 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2668. Min Act: -0.1700

Data Index: 991347 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.2356. Min Act: -0.1700

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1731. Min Act: -0.1700

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1418. Min Act: -0.1700

Data Index: 635126 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1106. Min Act: -0.1700

Data Index: 537827 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1731. Min Act: -0.1700

Data Index: 1103096 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1106. Min Act: -0.1700

Data Index: 951660 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1106. Min Act: -0.1700

Data Index: 1338174 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0793. Min Act: -0.1700

Data Index: 1151150 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0481. Min Act: -0.1700

Data Index: 358891 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.1106. Min Act: -0.1700

Data Index: 101180 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0793. Min Act: -0.1700

Data Index: 1106605 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0481. Min Act: -0.1700

Data Index: 183010 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0168. Min Act: -0.1700

Data Index: 730489 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 5.3293. Min Range: -5.3293

Max Act: 4.9856. Min Act: -0.1700

Data Index: 876387 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 5.3293. Min Range: -5.3293

Max Act: 5.0481. Min Act: -0.1700

Data Index: 942823 (C4 (Web Text))

Max Activating Token Index: 408