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

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

Neuron 1675 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.4182. Min Act: -0.1700

Data Index: 1006804 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.4495. Min Act: -0.1700

Data Index: 506459 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.3870. Min Act: -0.1700

Data Index: 1193230 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.4182. Min Act: -0.1700

Data Index: 1303743 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.3557. Min Act: -0.1700

Data Index: 519874 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.3245. Min Act: -0.1700

Data Index: 1254824 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.3557. Min Act: -0.1700

Data Index: 86789 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.3245. Min Act: -0.1700

Data Index: 1175948 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2932. Min Act: -0.1700

Data Index: 393011 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2932. Min Act: -0.1700

Data Index: 1195828 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2932. Min Act: -0.1700

Data Index: 1128151 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2307. Min Act: -0.1700

Data Index: 865593 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2619. Min Act: -0.1700

Data Index: 661737 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2619. Min Act: -0.1700

Data Index: 269629 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2307. Min Act: -0.1700

Data Index: 910144 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2307. Min Act: -0.1700

Data Index: 1200330 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2307. Min Act: -0.1700

Data Index: 1329819 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.1682. Min Act: -0.1700

Data Index: 443669 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.1994. Min Act: -0.1700

Data Index: 315715 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 4.4495. Min Range: -4.4495

Max Act: 4.2307. Min Act: -0.1700

Data Index: 111976 (C4 (Web Text))

Max Activating Token Index: 96