Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 600 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.3729. Min Act: -0.1700

Data Index: 466489 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.3267. Min Act: -0.1700

Data Index: 1281860 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2644. Min Act: -0.1700

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2346. Min Act: -0.1700

Data Index: 242285 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2344. Min Act: -0.1700

Data Index: 451601 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2299. Min Act: -0.1700

Data Index: 141349 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2292. Min Act: -0.1700

Data Index: 982624 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2412. Min Act: -0.1700

Data Index: 154554 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2226. Min Act: -0.1700

Data Index: 62433 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2009. Min Act: -0.1700

Data Index: 237605 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1841. Min Act: -0.1700

Data Index: 1353339 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.2037. Min Act: -0.1700

Data Index: 601525 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1888. Min Act: -0.1700

Data Index: 1216040 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1686. Min Act: -0.1700

Data Index: 333713 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1765. Min Act: -0.1700

Data Index: 80417 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1621. Min Act: -0.1700

Data Index: 410023 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1659. Min Act: -0.1700

Data Index: 73624 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1610. Min Act: -0.1700

Data Index: 883083 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1532. Min Act: -0.1700

Data Index: 38873 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 3.3729. Min Range: -3.3729

Max Act: 3.1412. Min Act: -0.1700

Data Index: 967285 (C4 (Web Text))

Max Activating Token Index: 455