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

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

Neuron 192 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: 3.3232. Min Range: -3.3232

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1285301 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2835. Min Act: -0.1700

Data Index: 706260 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2846. Min Act: -0.1700

Data Index: 1048986 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2449. Min Act: -0.1700

Data Index: 1127439 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2423. Min Act: -0.1700

Data Index: 632677 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2214. Min Act: -0.1700

Data Index: 241021 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2062. Min Act: -0.1700

Data Index: 1216478 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2070. Min Act: -0.1700

Data Index: 870341 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1998. Min Act: -0.1700

Data Index: 514115 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.2020. Min Act: -0.1700

Data Index: 791188 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1875. Min Act: -0.1700

Data Index: 327680 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1894. Min Act: -0.1700

Data Index: 963235 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1760. Min Act: -0.1700

Data Index: 640438 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1815. Min Act: -0.1700

Data Index: 412820 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1823. Min Act: -0.1699

Data Index: 429327 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1607. Min Act: -0.1700

Data Index: 98521 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1577. Min Act: -0.1700

Data Index: 935000 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1744. Min Act: -0.1700

Data Index: 266306 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1616. Min Act: -0.1700

Data Index: 601127 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.3232. Min Range: -3.3232

Max Act: 3.1529. Min Act: -0.1700

Data Index: 568953 (C4 (Web Text))

Max Activating Token Index: 1000