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

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

Neuron 1810 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1160. Min Range: -5.1160

Max Act: 5.1160. Min Act: -0.1700

Data Index: 1179196 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 5.1160. Min Range: -5.1160

Max Act: 5.0223. Min Act: -0.1700

Data Index: 371713 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9598. Min Act: -0.1700

Data Index: 1097663 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8660. Min Act: -0.1700

Data Index: 1052937 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9910. Min Act: -0.1700

Data Index: 324215 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9285. Min Act: -0.1700

Data Index: 617704 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9598. Min Act: -0.1700

Data Index: 1111902 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9598. Min Act: -0.1700

Data Index: 304933 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.7723. Min Act: -0.1700

Data Index: 927799 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9598. Min Act: -0.1700

Data Index: 623770 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9285. Min Act: -0.1700

Data Index: 340727 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8973. Min Act: -0.1700

Data Index: 264882 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8660. Min Act: -0.1700

Data Index: 1522555 (Python Code)

Max Activating Token Index: 792

Text #13

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8660. Min Act: -0.1700

Data Index: 1027053 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8348. Min Act: -0.1700

Data Index: 348777 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8348. Min Act: -0.1700

Data Index: 743956 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.7723. Min Act: -0.1700

Data Index: 222666 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8035. Min Act: -0.1700

Data Index: 816230 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.8035. Min Act: -0.1700

Data Index: 181276 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 5.1160. Min Range: -5.1160

Max Act: 4.9285. Min Act: -0.1700

Data Index: 987396 (C4 (Web Text))

Max Activating Token Index: 773