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

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

Neuron 1524 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: 5.8774. Min Range: -5.8774

Max Act: 5.8774. Min Act: -0.1700

Data Index: 629852 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7524. Min Act: -0.1700

Data Index: 204410 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7836. Min Act: -0.1699

Data Index: 634894 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7211. Min Act: -0.1700

Data Index: 366794 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7524. Min Act: -0.1700

Data Index: 1006397 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.6586. Min Act: -0.1700

Data Index: 693958 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7211. Min Act: -0.1700

Data Index: 629738 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.7211. Min Act: -0.1700

Data Index: 61533 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.6274. Min Act: -0.1700

Data Index: 277017 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5961. Min Act: -0.1700

Data Index: 1343769 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5649. Min Act: -0.1700

Data Index: 552674 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5336. Min Act: -0.1700

Data Index: 308255 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5649. Min Act: -0.1700

Data Index: 1299143 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5649. Min Act: -0.1700

Data Index: 1309769 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5024. Min Act: -0.1700

Data Index: 1136652 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.3149. Min Act: -0.1700

Data Index: 625558 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.4399. Min Act: -0.1700

Data Index: 957948 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5024. Min Act: -0.1700

Data Index: 759124 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.5961. Min Act: -0.1700

Data Index: 509442 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 5.8774. Min Range: -5.8774

Max Act: 5.4711. Min Act: -0.1700

Data Index: 425335 (C4 (Web Text))

Max Activating Token Index: 419