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

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

Neuron 1127 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: 3.5042. Min Range: -3.5042

Max Act: 3.5042. Min Act: -0.1700

Data Index: 30236 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.4729. Min Act: -0.1700

Data Index: 1029156 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3788. Min Act: -0.1700

Data Index: 1319398 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3945. Min Act: -0.1700

Data Index: 1330001 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3317. Min Act: -0.1700

Data Index: 205005 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2374. Min Act: -0.1700

Data Index: 1607198 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2846. Min Act: -0.1700

Data Index: 194858 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3003. Min Act: -0.1700

Data Index: 1217225 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.3160. Min Act: -0.1700

Data Index: 1109745 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2532. Min Act: -0.1700

Data Index: 155820 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2532. Min Act: -0.1700

Data Index: 495457 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1012480 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2374. Min Act: -0.1700

Data Index: 868610 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2532. Min Act: -0.1700

Data Index: 1092731 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2060. Min Act: -0.1700

Data Index: 317548 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2532. Min Act: -0.1700

Data Index: 726323 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2374. Min Act: -0.1700

Data Index: 1065138 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2374. Min Act: -0.1700

Data Index: 1260848 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2374. Min Act: -0.1700

Data Index: 1307604 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 3.5042. Min Range: -3.5042

Max Act: 3.2217. Min Act: -0.1700

Data Index: 902837 (C4 (Web Text))

Max Activating Token Index: 89