Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 578 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1419. Min Act: -0.1700

Data Index: 648670 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.1419. Min Act: -0.1700

Data Index: 916592 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0946. Min Act: -0.1700

Data Index: 447854 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0630. Min Act: -0.1700

Data Index: 550837 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0473. Min Act: -0.1700

Data Index: 1194922 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0473. Min Act: -0.1700

Data Index: 231284 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0315. Min Act: -0.1700

Data Index: 84622 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.1419. Min Range: -3.1419

Max Act: 3.0157. Min Act: -0.1700

Data Index: 1315237 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9840. Min Act: -0.1700

Data Index: 340393 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9840. Min Act: -0.1700

Data Index: 1359103 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9999. Min Act: -0.1700

Data Index: 606985 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9524. Min Act: -0.1700

Data Index: 447523 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9840. Min Act: -0.1700

Data Index: 585374 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9366. Min Act: -0.1700

Data Index: 1008512 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9524. Min Act: -0.1700

Data Index: 485967 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9366. Min Act: -0.1700

Data Index: 539810 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9366. Min Act: -0.1700

Data Index: 151640 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9366. Min Act: -0.1700

Data Index: 1028350 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9366. Min Act: -0.1700

Data Index: 886147 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 3.1419. Min Range: -3.1419

Max Act: 2.9207. Min Act: -0.1700

Data Index: 47064 (C4 (Web Text))

Max Activating Token Index: 879