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

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

Neuron 1367 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: 3.7070. Min Range: -3.7070

Max Act: 3.7070. Min Act: -0.1700

Data Index: 972151 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.7070. Min Act: -0.1700

Data Index: 981926 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.6444. Min Act: -0.1700

Data Index: 407340 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.6131. Min Act: -0.1700

Data Index: 956401 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5817. Min Act: -0.1700

Data Index: 359599 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5661. Min Act: -0.1700

Data Index: 488366 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4878. Min Act: -0.1700

Data Index: 997667 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5348. Min Act: -0.1700

Data Index: 815194 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5348. Min Act: -0.1700

Data Index: 533613 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5504. Min Act: -0.1700

Data Index: 734179 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5348. Min Act: -0.1700

Data Index: 1316472 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5504. Min Act: -0.1700

Data Index: 801784 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4407. Min Act: -0.1700

Data Index: 513855 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.5034. Min Act: -0.1700

Data Index: 552031 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4564. Min Act: -0.1700

Data Index: 502339 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4564. Min Act: -0.1700

Data Index: 421811 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4407. Min Act: -0.1700

Data Index: 677880 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4407. Min Act: -0.1700

Data Index: 553884 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4250. Min Act: -0.1700

Data Index: 554296 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.7070. Min Range: -3.7070

Max Act: 3.4250. Min Act: -0.1700

Data Index: 869494 (C4 (Web Text))

Max Activating Token Index: 317