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

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

Neuron 872 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: 3.8547. Min Range: -3.8547

Max Act: 3.8547. Min Act: -0.1700

Data Index: 724144 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7922. Min Act: -0.1700

Data Index: 735056 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7609. Min Act: -0.1700

Data Index: 878946 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1085355 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.8547. Min Act: -0.1700

Data Index: 209064 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.8547. Min Act: -0.1700

Data Index: 1128135 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7922. Min Act: -0.1700

Data Index: 545545 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6983. Min Act: -0.1700

Data Index: 8372 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 534477 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7609. Min Act: -0.1700

Data Index: 546910 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7609. Min Act: -0.1700

Data Index: 835059 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 284075 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7609. Min Act: -0.1700

Data Index: 551142 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 595633 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 841766 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 88748 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 345454 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.6670. Min Act: -0.1700

Data Index: 904671 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7296. Min Act: -0.1700

Data Index: 10419 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.8547. Min Range: -3.8547

Max Act: 3.7922. Min Act: -0.1700

Data Index: 907604 (C4 (Web Text))

Max Activating Token Index: 350