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

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

Neuron 1176 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1286. Min Range: -5.1286

Max Act: 5.1286. Min Act: -0.1700

Data Index: 824229 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8786. Min Act: -0.1700

Data Index: 332877 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.9411. Min Act: -0.1700

Data Index: 734134 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.9099. Min Act: -0.1700

Data Index: 90273 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8474. Min Act: -0.1700

Data Index: 1342491 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7536. Min Act: -0.1700

Data Index: 456933 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6599. Min Act: -0.1700

Data Index: 307322 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7849. Min Act: -0.1700

Data Index: 975200 (C4 (Web Text))

Max Activating Token Index: 403

Text #8

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6286. Min Act: -0.1700

Data Index: 372807 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6599. Min Act: -0.1700

Data Index: 982737 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6599. Min Act: -0.1700

Data Index: 945459 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5661. Min Act: -0.1700

Data Index: 685610 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6599. Min Act: -0.1700

Data Index: 1270742 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5974. Min Act: -0.1700

Data Index: 958200 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5974. Min Act: -0.1700

Data Index: 1210061 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6599. Min Act: -0.1700

Data Index: 545224 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5974. Min Act: -0.1700

Data Index: 318538 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5974. Min Act: -0.1700

Data Index: 1108979 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5974. Min Act: -0.1700

Data Index: 1033330 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5661. Min Act: -0.1700

Data Index: 988505 (C4 (Web Text))

Max Activating Token Index: 289