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

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

Neuron 1316 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.6316. Min Act: -0.1700

Data Index: 46340 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.6316. Min Act: -0.1700

Data Index: 1190091 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.6942. Min Act: -0.1700

Data Index: 728071 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.6003. Min Act: -0.1700

Data Index: 330555 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5689. Min Act: -0.1700

Data Index: 186203 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5689. Min Act: -0.1700

Data Index: 922025 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5689. Min Act: -0.1700

Data Index: 791004 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1176184 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5376. Min Act: -0.1700

Data Index: 285536 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5063. Min Act: -0.1700

Data Index: 1276771 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5063. Min Act: -0.1700

Data Index: 778178 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5220. Min Act: -0.1700

Data Index: 333199 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5376. Min Act: -0.1700

Data Index: 155972 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1227043 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5063. Min Act: -0.1700

Data Index: 3697 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5376. Min Act: -0.1700

Data Index: 732858 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1130815 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.5376. Min Act: -0.1700

Data Index: 486213 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1169721 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 3.6942. Min Range: -3.6942

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1357200 (C4 (Web Text))

Max Activating Token Index: 744