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

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

Neuron 1185 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7988. Min Act: -0.1700

Data Index: 504580 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1314161 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.7050. Min Act: -0.1700

Data Index: 908550 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.6267. Min Act: -0.1700

Data Index: 118669 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5641. Min Act: -0.1700

Data Index: 488425 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5641. Min Act: -0.1700

Data Index: 165593 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5798. Min Act: -0.1700

Data Index: 1238562 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5641. Min Act: -0.1700

Data Index: 742933 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5014. Min Act: -0.1700

Data Index: 736200 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5484. Min Act: -0.1700

Data Index: 28914 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5484. Min Act: -0.1700

Data Index: 455749 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5328. Min Act: -0.1700

Data Index: 961838 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4858. Min Act: -0.1700

Data Index: 449363 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5171. Min Act: -0.1700

Data Index: 482414 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4858. Min Act: -0.1700

Data Index: 475277 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5328. Min Act: -0.1700

Data Index: 65121 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4858. Min Act: -0.1700

Data Index: 713239 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.5014. Min Act: -0.1700

Data Index: 434518 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4701. Min Act: -0.1700

Data Index: 664819 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 3.7988. Min Range: -3.7988

Max Act: 3.4701. Min Act: -0.1700

Data Index: 1003229 (C4 (Web Text))

Max Activating Token Index: 699