Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1801 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.1341. Min Range: -7.1341

Max Act: 7.1341. Min Act: -0.1700

Data Index: 197276 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 7.1341. Min Range: -7.1341

Max Act: 7.0091. Min Act: -0.1700

Data Index: 102185 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.7591. Min Act: -0.1700

Data Index: 483052 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.7279. Min Act: -0.1699

Data Index: 820029 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5404. Min Act: -0.1700

Data Index: 405366 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5716. Min Act: -0.1698

Data Index: 31685 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5716. Min Act: -0.1700

Data Index: 1040888 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5404. Min Act: -0.1699

Data Index: 369607 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4779. Min Act: -0.1700

Data Index: 389457 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5091. Min Act: -0.1700

Data Index: 391923 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4154. Min Act: -0.1700

Data Index: 364833 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4466. Min Act: -0.1700

Data Index: 276237 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4154. Min Act: -0.1700

Data Index: 1171228 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.3841. Min Act: -0.1700

Data Index: 1108700 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4466. Min Act: -0.1700

Data Index: 499822 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.5716. Min Act: -0.1700

Data Index: 874226 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.3841. Min Act: -0.1700

Data Index: 1289163 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4154. Min Act: -0.1700

Data Index: 91990 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4466. Min Act: -0.1700

Data Index: 1003046 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 7.1341. Min Range: -7.1341

Max Act: 6.4154. Min Act: -0.1700

Data Index: 926428 (C4 (Web Text))

Max Activating Token Index: 195