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

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

Neuron 1942 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: 3.2372. Min Range: -3.2372

Max Act: 3.2372. Min Act: -0.1700

Data Index: 1603660 (Python Code)

Max Activating Token Index: 929

Text #1

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.7979. Min Act: -0.1700

Data Index: 1512567 (Python Code)

Max Activating Token Index: 296

Text #2

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.7602. Min Act: -0.1700

Data Index: 1553209 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.7142. Min Act: -0.1700

Data Index: 1435283 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.6214. Min Act: -0.1700

Data Index: 1391348 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4759. Min Act: -0.1700

Data Index: 1539226 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4758. Min Act: -0.1700

Data Index: 1448432 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4802. Min Act: -0.1700

Data Index: 1417003 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4634. Min Act: -0.1700

Data Index: 1448828 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4723. Min Act: -0.1700

Data Index: 1655835 (Python Code)

Max Activating Token Index: 694

Text #10

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4788. Min Act: -0.1700

Data Index: 1498467 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4481. Min Act: -0.1700

Data Index: 1462356 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4590. Min Act: -0.1700

Data Index: 1541909 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4489. Min Act: -0.1700

Data Index: 1509698 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4376. Min Act: -0.1700

Data Index: 917354 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4428. Min Act: -0.1699

Data Index: 122008 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4310. Min Act: -0.1700

Data Index: 1565412 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4363. Min Act: -0.1700

Data Index: 1423600 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4230. Min Act: -0.1700

Data Index: 1468404 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 3.2372. Min Range: -3.2372

Max Act: 2.4150. Min Act: -0.1700

Data Index: 1579847 (Python Code)

Max Activating Token Index: 803