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

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

Neuron 640 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: 5.1263. Min Range: -5.1263

Max Act: 5.1263. Min Act: -0.1700

Data Index: 863871 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.9700. Min Act: -0.1700

Data Index: 314641 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.9388. Min Act: -0.1700

Data Index: 338846 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.9388. Min Act: -0.1700

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.8450. Min Act: -0.1700

Data Index: 550771 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.8138. Min Act: -0.1700

Data Index: 584106 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.8763. Min Act: -0.1700

Data Index: 1069132 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.8138. Min Act: -0.1700

Data Index: 1341627 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7200. Min Act: -0.1700

Data Index: 662234 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7200. Min Act: -0.1700

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7513. Min Act: -0.1700

Data Index: 633564 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7513. Min Act: -0.1700

Data Index: 1077139 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.6888. Min Act: -0.1700

Data Index: 1230056 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7200. Min Act: -0.1700

Data Index: 960216 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.6263. Min Act: -0.1700

Data Index: 230398 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.5950. Min Act: -0.1700

Data Index: 1060869 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.7200. Min Act: -0.1700

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.5950. Min Act: -0.1700

Data Index: 422522 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.6263. Min Act: -0.1700

Data Index: 1047391 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 5.1263. Min Range: -5.1263

Max Act: 4.5950. Min Act: -0.1700

Data Index: 518353 (C4 (Web Text))

Max Activating Token Index: 614