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

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

Neuron 91 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.9421. Min Act: -0.1700

Data Index: 1343670 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8795. Min Act: -0.1700

Data Index: 464502 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8482. Min Act: -0.1700

Data Index: 1283950 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8482. Min Act: -0.1700

Data Index: 337951 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8482. Min Act: -0.1700

Data Index: 156141 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8482. Min Act: -0.1700

Data Index: 304565 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8170. Min Act: -0.1700

Data Index: 616319 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.8482. Min Act: -0.1700

Data Index: 1029023 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7544. Min Act: -0.1700

Data Index: 491589 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7857. Min Act: -0.1700

Data Index: 824050 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7857. Min Act: -0.1700

Data Index: 190232 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7857. Min Act: -0.1700

Data Index: 559594 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7857. Min Act: -0.1700

Data Index: 349162 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7231. Min Act: -0.1700

Data Index: 1131020 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7231. Min Act: -0.1700

Data Index: 979370 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7231. Min Act: -0.1700

Data Index: 857767 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7544. Min Act: -0.1700

Data Index: 855751 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7544. Min Act: -0.1700

Data Index: 1260335 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7544. Min Act: -0.1700

Data Index: 410454 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 3.9421. Min Range: -3.9421

Max Act: 3.7231. Min Act: -0.1700

Data Index: 1066810 (C4 (Web Text))

Max Activating Token Index: 831