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

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

Neuron 464 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: 4.4032. Min Range: -4.4032

Max Act: 4.4032. Min Act: -0.1700

Data Index: 983990 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.3888. Min Act: -0.1700

Data Index: 66187 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.3833. Min Act: -0.1700

Data Index: 1498023 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.3058. Min Act: -0.1700

Data Index: 751441 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2953. Min Act: -0.1700

Data Index: 1328850 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2473. Min Act: -0.1700

Data Index: 195671 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2554. Min Act: -0.1700

Data Index: 21608 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2617. Min Act: -0.1700

Data Index: 464563 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2457. Min Act: -0.1700

Data Index: 1352960 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2201. Min Act: -0.1700

Data Index: 808149 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.1961. Min Act: -0.1700

Data Index: 368734 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2204. Min Act: -0.1700

Data Index: 288568 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2257. Min Act: -0.1700

Data Index: 318662 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2146. Min Act: -0.1700

Data Index: 268153 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.2208. Min Act: -0.1700

Data Index: 1256263 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.1896. Min Act: -0.1700

Data Index: 249396 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.1734. Min Act: -0.1700

Data Index: 1001470 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.0858. Min Act: -0.1700

Data Index: 799700 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.1613. Min Act: -0.1700

Data Index: 795322 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 4.4032. Min Range: -4.4032

Max Act: 4.1197. Min Act: -0.1700

Data Index: 459138 (C4 (Web Text))

Max Activating Token Index: 176