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

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

Neuron 1931 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: 3.6609. Min Range: -3.6609

Max Act: 3.6609. Min Act: -0.1700

Data Index: 7014 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1258793 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.6296. Min Act: -0.1700

Data Index: 398666 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.6140. Min Act: -0.1700

Data Index: 182568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5983. Min Act: -0.1700

Data Index: 1221791 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5200. Min Act: -0.1700

Data Index: 738978 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5513. Min Act: -0.1700

Data Index: 644051 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5513. Min Act: -0.1700

Data Index: 549443 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5357. Min Act: -0.1700

Data Index: 983172 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5357. Min Act: -0.1700

Data Index: 1281809 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5357. Min Act: -0.1700

Data Index: 249956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5200. Min Act: -0.1700

Data Index: 932257 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5043. Min Act: -0.1700

Data Index: 732371 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.5043. Min Act: -0.1700

Data Index: 558147 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4730. Min Act: -0.1700

Data Index: 48082 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4730. Min Act: -0.1700

Data Index: 208938 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4103. Min Act: -0.1700

Data Index: 29425 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4730. Min Act: -0.1700

Data Index: 458180 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4260. Min Act: -0.1700

Data Index: 218792 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.6609. Min Range: -3.6609

Max Act: 3.4260. Min Act: -0.1700

Data Index: 785652 (C4 (Web Text))

Max Activating Token Index: 778