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

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

Neuron 1810 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: 3.8348. Min Range: -3.8348

Max Act: 3.8348. Min Act: -0.1700

Data Index: 1209662 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.6783. Min Act: -0.1700

Data Index: 1357494 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.6783. Min Act: -0.1700

Data Index: 911592 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.7096. Min Act: -0.1700

Data Index: 1219306 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.6470. Min Act: -0.1700

Data Index: 37759 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5844. Min Act: -0.1700

Data Index: 99372 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.6157. Min Act: -0.1700

Data Index: 195137 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5531. Min Act: -0.1700

Data Index: 404902 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5844. Min Act: -0.1700

Data Index: 131709 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1333923 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1115257 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5217. Min Act: -0.1700

Data Index: 498108 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5531. Min Act: -0.1700

Data Index: 632511 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5531. Min Act: -0.1700

Data Index: 157623 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5217. Min Act: -0.1700

Data Index: 181029 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5217. Min Act: -0.1700

Data Index: 924606 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5531. Min Act: -0.1700

Data Index: 1165868 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.5217. Min Act: -0.1700

Data Index: 940705 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.4904. Min Act: -0.1700

Data Index: 399516 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 3.8348. Min Range: -3.8348

Max Act: 3.4904. Min Act: -0.1700

Data Index: 991277 (C4 (Web Text))

Max Activating Token Index: 777