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

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

Neuron 1675 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: 3.4575. Min Range: -3.4575

Max Act: 3.4575. Min Act: -0.1700

Data Index: 631838 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.4554. Min Act: -0.1700

Data Index: 1217458 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.4155. Min Act: -0.1700

Data Index: 690463 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.4067. Min Act: -0.1700

Data Index: 1149683 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3941. Min Act: -0.1700

Data Index: 755014 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3976. Min Act: -0.1700

Data Index: 894649 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3541. Min Act: -0.1700

Data Index: 1123163 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3632. Min Act: -0.1699

Data Index: 1193774 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3649. Min Act: -0.1698

Data Index: 1157664 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3561. Min Act: -0.1700

Data Index: 733154 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3348. Min Act: -0.1700

Data Index: 1042439 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3446. Min Act: -0.1700

Data Index: 610674 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3001. Min Act: -0.1700

Data Index: 811238 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3034. Min Act: -0.1700

Data Index: 18633 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3149. Min Act: -0.1700

Data Index: 189067 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.2978. Min Act: -0.1700

Data Index: 1316517 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3044. Min Act: -0.1700

Data Index: 25064 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3091. Min Act: -0.1700

Data Index: 1009226 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3165. Min Act: -0.1699

Data Index: 309281 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 3.4575. Min Range: -3.4575

Max Act: 3.3051. Min Act: -0.1700

Data Index: 409708 (C4 (Web Text))

Max Activating Token Index: 627