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

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

Neuron 423 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: 3.8647. Min Range: -3.8647

Max Act: 3.8647. Min Act: -0.1700

Data Index: 827988 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.8634. Min Act: -0.1700

Data Index: 1239162 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.8318. Min Act: -0.1700

Data Index: 374032 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7794. Min Act: -0.1700

Data Index: 463274 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7594. Min Act: -0.1700

Data Index: 489671 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7360. Min Act: -0.1700

Data Index: 1082717 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7143. Min Act: -0.1700

Data Index: 1233469 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7129. Min Act: -0.1700

Data Index: 476225 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7082. Min Act: -0.1700

Data Index: 1276540 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.7075. Min Act: -0.1700

Data Index: 143845 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6973. Min Act: -0.1700

Data Index: 510445 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6707. Min Act: -0.1700

Data Index: 347977 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6659. Min Act: -0.1700

Data Index: 535710 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6639. Min Act: -0.1700

Data Index: 81435 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6582. Min Act: -0.1700

Data Index: 1090319 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6644. Min Act: -0.1700

Data Index: 1297639 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6656. Min Act: -0.1700

Data Index: 1292848 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6697. Min Act: -0.1700

Data Index: 750359 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6620. Min Act: -0.1700

Data Index: 1006029 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.8647. Min Range: -3.8647

Max Act: 3.6455. Min Act: -0.1700

Data Index: 154347 (C4 (Web Text))

Max Activating Token Index: 464