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

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

Neuron 1281 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: 4.5470. Min Range: -4.5470

Max Act: 4.5470. Min Act: -0.1700

Data Index: 1639524 (Python Code)

Max Activating Token Index: 446

Text #1

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.5058. Min Act: -0.1700

Data Index: 1448014 (Python Code)

Max Activating Token Index: 420

Text #2

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.5224. Min Act: -0.1700

Data Index: 1382307 (Python Code)

Max Activating Token Index: 85

Text #3

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.4335. Min Act: -0.1700

Data Index: 1381225 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.3666. Min Act: -0.1700

Data Index: 1636191 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.3721. Min Act: -0.1700

Data Index: 1421282 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.2423. Min Act: -0.1700

Data Index: 1606682 (Python Code)

Max Activating Token Index: 413

Text #7

Max Range: 4.5470. Min Range: -4.5470

Max Act: 4.2144. Min Act: -0.1700

Data Index: 1439475 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.9386. Min Act: -0.1700

Data Index: 395423 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.9188. Min Act: -0.1700

Data Index: 1364983 (Python Code)

Max Activating Token Index: 589

Text #10

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.7868. Min Act: -0.1700

Data Index: 279840 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.7309. Min Act: -0.1700

Data Index: 633555 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.7151. Min Act: -0.1700

Data Index: 1541169 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.7234. Min Act: -0.1700

Data Index: 38837 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.7104. Min Act: -0.1700

Data Index: 1520295 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.6982. Min Act: -0.1700

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.6613. Min Act: -0.1700

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.6502. Min Act: -0.1700

Data Index: 508940 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.6372. Min Act: -0.1700

Data Index: 1468759 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 4.5470. Min Range: -4.5470

Max Act: 3.6201. Min Act: -0.1700

Data Index: 926498 (C4 (Web Text))

Max Activating Token Index: 297