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

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

Neuron 1165 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: 4.5312. Min Range: -4.5312

Max Act: 4.5312. Min Act: -0.1696

Data Index: 177500 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.4700. Min Act: -0.1700

Data Index: 78391 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.4360. Min Act: -0.1700

Data Index: 1540424 (Python Code)

Max Activating Token Index: 80

Text #3

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.4028. Min Act: -0.1700

Data Index: 880414 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3720. Min Act: -0.1697

Data Index: 630164 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3650. Min Act: -0.1700

Data Index: 717802 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3378. Min Act: -0.1499

Data Index: 1231400 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3523. Min Act: -0.1663

Data Index: 379775 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3279. Min Act: -0.1696

Data Index: 1213835 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3258. Min Act: -0.1667

Data Index: 1297195 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3258. Min Act: -0.1682

Data Index: 995925 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2869. Min Act: -0.1699

Data Index: 1221087 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3070. Min Act: -0.1696

Data Index: 428768 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.3084. Min Act: -0.1698

Data Index: 599369 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2719. Min Act: -0.1184

Data Index: 1644198 (Python Code)

Max Activating Token Index: 611

Text #15

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2735. Min Act: -0.1695

Data Index: 1136544 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2480. Min Act: -0.1700

Data Index: 1318546 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2728. Min Act: -0.1690

Data Index: 1196666 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2634. Min Act: -0.1687

Data Index: 689341 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 4.5312. Min Range: -4.5312

Max Act: 4.2679. Min Act: -0.1700

Data Index: 271573 (C4 (Web Text))

Max Activating Token Index: 737