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

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

Neuron 243 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0236. Min Range: -6.0236

Max Act: 6.0236. Min Act: -0.1700

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.9220. Min Act: -0.1700

Data Index: 1005376 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.8986. Min Act: -0.1700

Data Index: 327088 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.8517. Min Act: -0.1700

Data Index: 1045677 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.8127. Min Act: -0.1700

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.7502. Min Act: -0.1700

Data Index: 1189312 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6798. Min Act: -0.1699

Data Index: 304053 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6955. Min Act: -0.1700

Data Index: 908223 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.7267. Min Act: -0.1700

Data Index: 364407 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5939. Min Act: -0.1700

Data Index: 907724 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6330. Min Act: -0.1700

Data Index: 889991 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5548. Min Act: -0.1700

Data Index: 809544 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6252. Min Act: -0.1700

Data Index: 1317195 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5861. Min Act: -0.1700

Data Index: 722230 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5939. Min Act: -0.1700

Data Index: 425024 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6017. Min Act: -0.1700

Data Index: 833292 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5314. Min Act: -0.1700

Data Index: 735350 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5861. Min Act: -0.1700

Data Index: 312069 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.6017. Min Act: -0.1700

Data Index: 763218 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 6.0236. Min Range: -6.0236

Max Act: 5.5314. Min Act: -0.1700

Data Index: 783112 (C4 (Web Text))

Max Activating Token Index: 145