Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 345 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.5584. Min Act: -0.1700

Data Index: 849535 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.6210. Min Act: -0.1700

Data Index: 1026572 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.5897. Min Act: -0.1700

Data Index: 493371 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.5271. Min Act: -0.1700

Data Index: 828012 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.5584. Min Act: -0.1700

Data Index: 443125 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4331. Min Act: -0.1700

Data Index: 1091602 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4644. Min Act: -0.1700

Data Index: 1158538 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4644. Min Act: -0.1700

Data Index: 1097960 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4644. Min Act: -0.1700

Data Index: 749542 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4957. Min Act: -0.1700

Data Index: 828398 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4487. Min Act: -0.1700

Data Index: 489770 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4174. Min Act: -0.1700

Data Index: 964529 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4487. Min Act: -0.1700

Data Index: 149741 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4174. Min Act: -0.1700

Data Index: 331344 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4017. Min Act: -0.1700

Data Index: 530302 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4644. Min Act: -0.1700

Data Index: 621027 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4017. Min Act: -0.1700

Data Index: 853044 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4017. Min Act: -0.1700

Data Index: 139707 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1191243 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 3.6210. Min Range: -3.6210

Max Act: 3.4174. Min Act: -0.1700

Data Index: 187188 (C4 (Web Text))

Max Activating Token Index: 912