Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 273 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.5054. Min Act: -0.1700

Data Index: 947252 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.5054. Min Act: -0.1700

Data Index: 442903 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4742. Min Act: -0.1700

Data Index: 748716 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4742. Min Act: -0.1700

Data Index: 265139 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4117. Min Act: -0.1700

Data Index: 455986 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4117. Min Act: -0.1700

Data Index: 788720 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4429. Min Act: -0.1700

Data Index: 666976 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3179. Min Act: -0.1700

Data Index: 353416 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3804. Min Act: -0.1700

Data Index: 343348 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3179. Min Act: -0.1700

Data Index: 866377 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4117. Min Act: -0.1700

Data Index: 984381 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3492. Min Act: -0.1700

Data Index: 2919 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3492. Min Act: -0.1700

Data Index: 158729 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4117. Min Act: -0.1700

Data Index: 1288008 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3492. Min Act: -0.1700

Data Index: 83421 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3179. Min Act: -0.1700

Data Index: 733999 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3492. Min Act: -0.1700

Data Index: 443908 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.3804. Min Act: -0.1700

Data Index: 1206145 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.4117. Min Act: -0.1700

Data Index: 1017180 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 5.5054. Min Range: -5.5054

Max Act: 5.2867. Min Act: -0.1700

Data Index: 731464 (C4 (Web Text))

Max Activating Token Index: 309