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

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

Neuron 996 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: 4.2494. Min Range: -4.2494

Max Act: 4.2494. Min Act: -0.1700

Data Index: 721585 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.8837. Min Act: -0.1700

Data Index: 395784 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7821. Min Act: -0.1700

Data Index: 1173462 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7410. Min Act: -0.1700

Data Index: 513014 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7446. Min Act: -0.1700

Data Index: 49944 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7304. Min Act: -0.1700

Data Index: 1127513 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7419. Min Act: -0.1700

Data Index: 598755 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1186684 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.7220. Min Act: -0.1700

Data Index: 1334840 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6787. Min Act: -0.1700

Data Index: 613345 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6934. Min Act: -0.1700

Data Index: 471623 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6569. Min Act: -0.1700

Data Index: 309291 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6888. Min Act: -0.1700

Data Index: 1016112 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6623. Min Act: -0.1700

Data Index: 229808 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6412. Min Act: -0.1700

Data Index: 1017094 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6236. Min Act: -0.1700

Data Index: 952029 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6477. Min Act: -0.1700

Data Index: 54179 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6275. Min Act: -0.1700

Data Index: 425850 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1211693 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 4.2494. Min Range: -4.2494

Max Act: 3.5977. Min Act: -0.1700

Data Index: 397061 (C4 (Web Text))

Max Activating Token Index: 550