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

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

Neuron 234 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: 3.4874. Min Range: -3.4874

Max Act: 3.4561. Min Act: -0.1700

Data Index: 890448 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4874. Min Act: -0.1700

Data Index: 88116 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4874. Min Act: -0.1700

Data Index: 88361 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4874. Min Act: -0.1700

Data Index: 359898 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3620. Min Act: -0.1700

Data Index: 214751 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3620. Min Act: -0.1700

Data Index: 916887 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3620. Min Act: -0.1700

Data Index: 524369 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.4247. Min Act: -0.1700

Data Index: 1256856 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3934. Min Act: -0.1700

Data Index: 952617 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.2992. Min Act: -0.1700

Data Index: 216551 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3620. Min Act: -0.1700

Data Index: 185785 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3620. Min Act: -0.1700

Data Index: 637124 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3149. Min Act: -0.1700

Data Index: 1265277 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1263318 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3149. Min Act: -0.1700

Data Index: 1236909 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.2992. Min Act: -0.1700

Data Index: 306069 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3306. Min Act: -0.1700

Data Index: 326729 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.3149. Min Act: -0.1700

Data Index: 1272647 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1149188 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 3.4874. Min Range: -3.4874

Max Act: 3.2835. Min Act: -0.1700

Data Index: 1164348 (C4 (Web Text))

Max Activating Token Index: 227