Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1987 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.7121. Min Act: -0.1700

Data Index: 1248355 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.7121. Min Act: -0.1700

Data Index: 621902 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.6338. Min Act: -0.1700

Data Index: 587443 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.6651. Min Act: -0.1700

Data Index: 894539 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.6025. Min Act: -0.1700

Data Index: 135959 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5712. Min Act: -0.1700

Data Index: 432376 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5868. Min Act: -0.1700

Data Index: 1262536 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5712. Min Act: -0.1700

Data Index: 1261277 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5712. Min Act: -0.1700

Data Index: 532251 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5712. Min Act: -0.1700

Data Index: 739775 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5555. Min Act: -0.1700

Data Index: 334326 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5399. Min Act: -0.1700

Data Index: 289567 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5399. Min Act: -0.1700

Data Index: 362687 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5242. Min Act: -0.1700

Data Index: 877791 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5085. Min Act: -0.1700

Data Index: 962882 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5085. Min Act: -0.1700

Data Index: 619942 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.4929. Min Act: -0.1700

Data Index: 805257 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.4929. Min Act: -0.1700

Data Index: 634088 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.5242. Min Act: -0.1700

Data Index: 232271 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.7121. Min Range: -3.7121

Max Act: 3.4929. Min Act: -0.1700

Data Index: 524536 (C4 (Web Text))

Max Activating Token Index: 485