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

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

Neuron 1211 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: 5.6170. Min Range: -5.6170

Max Act: 5.6170. Min Act: -0.1699

Data Index: 1069239 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4608. Min Act: -0.1700

Data Index: 1214632 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4608. Min Act: -0.1700

Data Index: 1532448 (Python Code)

Max Activating Token Index: 281

Text #3

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4295. Min Act: -0.1700

Data Index: 1141810 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4295. Min Act: -0.1700

Data Index: 902051 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4608. Min Act: -0.1700

Data Index: 148089 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3670. Min Act: -0.1700

Data Index: 485135 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4295. Min Act: -0.1700

Data Index: 274126 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3983. Min Act: -0.1700

Data Index: 1331614 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.4295. Min Act: -0.1700

Data Index: 529624 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3670. Min Act: -0.1700

Data Index: 625368 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3358. Min Act: -0.1700

Data Index: 1484384 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3045. Min Act: -0.1700

Data Index: 1057505 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3358. Min Act: -0.1700

Data Index: 1317559 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3358. Min Act: -0.1700

Data Index: 695825 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.3045. Min Act: -0.1700

Data Index: 1134140 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.2420. Min Act: -0.1700

Data Index: 914879 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.2420. Min Act: -0.1700

Data Index: 861276 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.2420. Min Act: -0.1700

Data Index: 1034962 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 5.6170. Min Range: -5.6170

Max Act: 5.2733. Min Act: -0.1700

Data Index: 549908 (C4 (Web Text))

Max Activating Token Index: 178