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

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

Neuron 336 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2483. Min Range: -6.2483

Max Act: 6.2483. Min Act: -0.1700

Data Index: 1154362 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 6.2483. Min Range: -6.2483

Max Act: 6.1858. Min Act: -0.1700

Data Index: 353321 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 6.2483. Min Range: -6.2483

Max Act: 6.1858. Min Act: -0.1700

Data Index: 795248 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.9358. Min Act: -0.1700

Data Index: 1082566 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8733. Min Act: -0.1700

Data Index: 334263 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8733. Min Act: -0.1700

Data Index: 671424 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8733. Min Act: -0.1700

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8420. Min Act: -0.1700

Data Index: 976548 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8420. Min Act: -0.1700

Data Index: 158692 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8420. Min Act: -0.1700

Data Index: 564844 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.8108. Min Act: -0.1700

Data Index: 784888 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.7483. Min Act: -0.1700

Data Index: 935165 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6545. Min Act: -0.1700

Data Index: 881369 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6858. Min Act: -0.1700

Data Index: 800070 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6858. Min Act: -0.1700

Data Index: 1215790 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6858. Min Act: -0.1700

Data Index: 1256826 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6545. Min Act: -0.1700

Data Index: 837535 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6545. Min Act: -0.1700

Data Index: 1349414 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6545. Min Act: -0.1700

Data Index: 431246 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 6.2483. Min Range: -6.2483

Max Act: 5.6545. Min Act: -0.1699

Data Index: 176986 (C4 (Web Text))

Max Activating Token Index: 48