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

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

Neuron 584 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.5581. Min Act: -0.1700

Data Index: 538766 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.5267. Min Act: -0.1700

Data Index: 684229 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.5267. Min Act: -0.1700

Data Index: 177961 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4954. Min Act: -0.1700

Data Index: 245714 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.5267. Min Act: -0.1700

Data Index: 1074697 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4954. Min Act: -0.1700

Data Index: 416735 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4954. Min Act: -0.1700

Data Index: 829275 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4954. Min Act: -0.1700

Data Index: 31281 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4954. Min Act: -0.1700

Data Index: 436219 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.5267. Min Act: -0.1700

Data Index: 484760 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4013. Min Act: -0.1700

Data Index: 979228 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4641. Min Act: -0.1700

Data Index: 315295 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4327. Min Act: -0.1700

Data Index: 1115299 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4641. Min Act: -0.1700

Data Index: 625037 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4327. Min Act: -0.1700

Data Index: 151503 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4641. Min Act: -0.1700

Data Index: 135799 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4641. Min Act: -0.1700

Data Index: 710653 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4327. Min Act: -0.1700

Data Index: 878915 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4327. Min Act: -0.1700

Data Index: 589204 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 3.5581. Min Range: -3.5581

Max Act: 3.4327. Min Act: -0.1700

Data Index: 1305532 (C4 (Web Text))

Max Activating Token Index: 494