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

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

Neuron 245 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: 5.1286. Min Range: -5.1286

Max Act: 5.1286. Min Act: -0.1700

Data Index: 250238 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.9724. Min Act: -0.1700

Data Index: 517760 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.9411. Min Act: -0.1700

Data Index: 302013 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.9099. Min Act: -0.1700

Data Index: 975409 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8474. Min Act: -0.1700

Data Index: 979241 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8786. Min Act: -0.1700

Data Index: 588905 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8474. Min Act: -0.1700

Data Index: 1232627 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7849. Min Act: -0.1700

Data Index: 421861 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 703753 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.8161. Min Act: -0.1700

Data Index: 868781 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7536. Min Act: -0.1700

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 185669 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 358796 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7849. Min Act: -0.1700

Data Index: 653591 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 530783 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6286. Min Act: -0.1700

Data Index: 1041446 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.7224. Min Act: -0.1700

Data Index: 393861 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.5349. Min Act: -0.1700

Data Index: 524864 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 5.1286. Min Range: -5.1286

Max Act: 4.6286. Min Act: -0.1700

Data Index: 733412 (C4 (Web Text))

Max Activating Token Index: 913