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

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

Neuron 1818 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: 3.5227. Min Range: -3.5227

Max Act: 3.5227. Min Act: -0.1700

Data Index: 286239 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.5004. Min Act: -0.1625

Data Index: 1556154 (Python Code)

Max Activating Token Index: 300

Text #2

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3972. Min Act: -0.1699

Data Index: 1499114 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.4051. Min Act: -0.1700

Data Index: 1468080 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3786. Min Act: -0.0903

Data Index: 1175819 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3502. Min Act: -0.1689

Data Index: 1483807 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3464. Min Act: -0.1677

Data Index: 554658 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3304. Min Act: -0.1689

Data Index: 1454916 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3321. Min Act: -0.1615

Data Index: 1375367 (Python Code)

Max Activating Token Index: 672

Text #9

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3196. Min Act: -0.0903

Data Index: 752242 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3278. Min Act: -0.1697

Data Index: 1093257 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3373. Min Act: -0.1697

Data Index: 1383034 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3209. Min Act: -0.0903

Data Index: 1455793 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2822. Min Act: -0.1700

Data Index: 1646159 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.3090. Min Act: -0.1680

Data Index: 1552072 (Python Code)

Max Activating Token Index: 934

Text #15

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2858. Min Act: -0.1699

Data Index: 1496379 (Python Code)

Max Activating Token Index: 352

Text #16

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2855. Min Act: -0.1700

Data Index: 1469604 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2853. Min Act: -0.1679

Data Index: 1532407 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2742. Min Act: -0.1700

Data Index: 301321 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.5227. Min Range: -3.5227

Max Act: 3.2444. Min Act: -0.1696

Data Index: 515072 (C4 (Web Text))

Max Activating Token Index: 564