Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1586 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 162973 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8985. Min Act: -0.1700

Data Index: 156407 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8360. Min Act: -0.1700

Data Index: 1286269 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8360. Min Act: -0.1700

Data Index: 253480 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8047. Min Act: -0.1700

Data Index: 617843 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8672. Min Act: -0.1700

Data Index: 436875 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8047. Min Act: -0.1700

Data Index: 291277 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8047. Min Act: -0.1700

Data Index: 441658 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8047. Min Act: -0.1700

Data Index: 1308309 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 857085 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 420450 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.8047. Min Act: -0.1700

Data Index: 522388 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 248357 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 589584 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 625753 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7734. Min Act: -0.1700

Data Index: 258464 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 656419 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 782149 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 99544 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 3.8985. Min Range: -3.8985

Max Act: 3.7421. Min Act: -0.1700

Data Index: 171370 (C4 (Web Text))

Max Activating Token Index: 913