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

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

Neuron 2006 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: 4.2575. Min Range: -4.2575

Max Act: 4.2575. Min Act: -0.1149

Data Index: 543706 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.1764. Min Act: -0.1700

Data Index: 1302442 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.1747. Min Act: -0.1700

Data Index: 13173 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.1224. Min Act: -0.1700

Data Index: 12277 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.1021. Min Act: -0.1698

Data Index: 482645 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.0435. Min Act: -0.1700

Data Index: 675164 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.0467. Min Act: -0.1700

Data Index: 460788 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.0243. Min Act: -0.1663

Data Index: 578825 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 4.2575. Min Range: -4.2575

Max Act: 4.0188. Min Act: -0.1700

Data Index: 1002744 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9795. Min Act: -0.1670

Data Index: 168486 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9475. Min Act: -0.1700

Data Index: 679564 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9507. Min Act: -0.1684

Data Index: 989528 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9599. Min Act: -0.1699

Data Index: 171152 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9531. Min Act: -0.1700

Data Index: 150527 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9304. Min Act: -0.0656

Data Index: 1465263 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9216. Min Act: -0.1700

Data Index: 596964 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9312. Min Act: -0.1700

Data Index: 677738 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.9140. Min Act: -0.1700

Data Index: 56762 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1270238 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 4.2575. Min Range: -4.2575

Max Act: 3.8822. Min Act: -0.1660

Data Index: 678681 (C4 (Web Text))

Max Activating Token Index: 1022