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

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

Neuron 698 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: 3.6459. Min Range: -3.6459

Max Act: 3.6459. Min Act: -0.1700

Data Index: 322097 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.6146. Min Act: -0.1700

Data Index: 926079 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.6146. Min Act: -0.1700

Data Index: 1224929 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5833. Min Act: -0.1700

Data Index: 1039725 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5206. Min Act: -0.1700

Data Index: 1121465 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5206. Min Act: -0.1700

Data Index: 419651 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4579. Min Act: -0.1700

Data Index: 585758 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.5206. Min Act: -0.1700

Data Index: 542427 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4893. Min Act: -0.1700

Data Index: 1134869 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1091074 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4893. Min Act: -0.1700

Data Index: 716703 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4266. Min Act: -0.1700

Data Index: 503655 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1260818 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4579. Min Act: -0.1700

Data Index: 1024738 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4266. Min Act: -0.1700

Data Index: 406608 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4266. Min Act: -0.1700

Data Index: 1236673 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3952. Min Act: -0.1700

Data Index: 143120 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.4579. Min Act: -0.1700

Data Index: 167283 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3952. Min Act: -0.1700

Data Index: 141463 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 3.6459. Min Range: -3.6459

Max Act: 3.3952. Min Act: -0.1700

Data Index: 719237 (C4 (Web Text))

Max Activating Token Index: 220