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

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

Neuron 334 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: 3.1952. Min Range: -3.1952

Max Act: 3.1952. Min Act: -0.1700

Data Index: 388887 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9902. Min Act: -0.1700

Data Index: 1030637 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9902. Min Act: -0.1700

Data Index: 359355 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9585. Min Act: -0.1700

Data Index: 87149 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9110. Min Act: -0.1700

Data Index: 962017 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.9110. Min Act: -0.1700

Data Index: 120993 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8793. Min Act: -0.1700

Data Index: 752478 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8793. Min Act: -0.1700

Data Index: 67651 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8475. Min Act: -0.1700

Data Index: 1029568 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8475. Min Act: -0.1700

Data Index: 352399 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8157. Min Act: -0.1700

Data Index: 661200 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8634. Min Act: -0.1700

Data Index: 1148100 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8316. Min Act: -0.1700

Data Index: 272351 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8157. Min Act: -0.1700

Data Index: 249544 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8316. Min Act: -0.1700

Data Index: 891422 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.8157. Min Act: -0.1700

Data Index: 831405 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7998. Min Act: -0.1700

Data Index: 986444 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7998. Min Act: -0.1700

Data Index: 483734 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7998. Min Act: -0.1700

Data Index: 1100034 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.1952. Min Range: -3.1952

Max Act: 2.7838. Min Act: -0.1700

Data Index: 555474 (C4 (Web Text))

Max Activating Token Index: 735