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

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

Neuron 1277 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.3033. Min Act: -0.1700

Data Index: 1075732 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2719. Min Act: -0.1700

Data Index: 1309448 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2719. Min Act: -0.1700

Data Index: 558999 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.2719. Min Act: -0.1700

Data Index: 480923 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1933. Min Act: -0.1700

Data Index: 563120 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1775. Min Act: -0.1700

Data Index: 421594 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1460. Min Act: -0.1700

Data Index: 811298 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1303. Min Act: -0.1700

Data Index: 349103 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1218599 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1460. Min Act: -0.1700

Data Index: 1198128 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1145. Min Act: -0.1700

Data Index: 1048857 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.1145. Min Act: -0.1700

Data Index: 765511 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0830. Min Act: -0.1700

Data Index: 824690 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0514. Min Act: -0.1700

Data Index: 732894 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0830. Min Act: -0.1700

Data Index: 794548 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0357. Min Act: -0.1700

Data Index: 1016063 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0672. Min Act: -0.1700

Data Index: 53657 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0514. Min Act: -0.1700

Data Index: 729390 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0514. Min Act: -0.1700

Data Index: 836159 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.3033. Min Range: -3.3033

Max Act: 3.0514. Min Act: -0.1700

Data Index: 1090165 (C4 (Web Text))

Max Activating Token Index: 366