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

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

Neuron 145 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: 3.9874. Min Range: -3.9874

Max Act: 3.9874. Min Act: -0.1700

Data Index: 575241 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8936. Min Act: -0.1700

Data Index: 516305 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8936. Min Act: -0.1700

Data Index: 758409 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8936. Min Act: -0.1700

Data Index: 923833 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 690448 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8310. Min Act: -0.1700

Data Index: 1095538 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 487390 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8310. Min Act: -0.1700

Data Index: 1306356 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 22386 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.8310. Min Act: -0.1700

Data Index: 692901 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 1092295 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1136900 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 659943 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 554840 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7685. Min Act: -0.1700

Data Index: 252702 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7997. Min Act: -0.1700

Data Index: 574916 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7685. Min Act: -0.1700

Data Index: 1186274 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7372. Min Act: -0.1700

Data Index: 545391 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7372. Min Act: -0.1700

Data Index: 1023423 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 3.9874. Min Range: -3.9874

Max Act: 3.7685. Min Act: -0.1700

Data Index: 288977 (C4 (Web Text))

Max Activating Token Index: 673