Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4318. Min Act: -0.1700

Data Index: 267214 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.3693. Min Act: -0.1700

Data Index: 155825 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4318. Min Act: -0.1700

Data Index: 462564 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.3693. Min Act: -0.1700

Data Index: 818245 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4005. Min Act: -0.1700

Data Index: 868568 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4005. Min Act: -0.1700

Data Index: 515452 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4005. Min Act: -0.1700

Data Index: 48823 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.3380. Min Act: -0.1700

Data Index: 176175 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2755. Min Act: -0.1700

Data Index: 877787 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.4005. Min Act: -0.1700

Data Index: 207041 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2755. Min Act: -0.1700

Data Index: 1263578 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.1818. Min Act: -0.1700

Data Index: 1290142 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.1505. Min Act: -0.1700

Data Index: 476333 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.1818. Min Act: -0.1700

Data Index: 1169067 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2443. Min Act: -0.1700

Data Index: 1081128 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2755. Min Act: -0.1700

Data Index: 342840 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2443. Min Act: -0.1700

Data Index: 836392 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2130. Min Act: -0.1700

Data Index: 1006518 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.1193. Min Act: -0.1700

Data Index: 23901 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 5.4318. Min Range: -5.4318

Max Act: 5.2130. Min Act: -0.1700

Data Index: 393045 (C4 (Web Text))

Max Activating Token Index: 915