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

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

Neuron 1432 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: 3.5288. Min Range: -3.5288

Max Act: 3.5288. Min Act: -0.1700

Data Index: 552162 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.5131. Min Act: -0.1700

Data Index: 634186 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1234081 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4348. Min Act: -0.1700

Data Index: 1197488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4348. Min Act: -0.1700

Data Index: 229846 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4348. Min Act: -0.1700

Data Index: 962753 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4034. Min Act: -0.1700

Data Index: 686376 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4034. Min Act: -0.1700

Data Index: 484973 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4191. Min Act: -0.1700

Data Index: 400352 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4348. Min Act: -0.1700

Data Index: 816284 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4034. Min Act: -0.1700

Data Index: 1168471 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4191. Min Act: -0.1700

Data Index: 1103341 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4191. Min Act: -0.1700

Data Index: 957612 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4034. Min Act: -0.1700

Data Index: 831770 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.3720. Min Act: -0.1700

Data Index: 128321 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.3564. Min Act: -0.1700

Data Index: 1113755 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.3564. Min Act: -0.1700

Data Index: 796000 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.3720. Min Act: -0.1700

Data Index: 956758 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.4034. Min Act: -0.1700

Data Index: 244638 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 3.5288. Min Range: -3.5288

Max Act: 3.3720. Min Act: -0.1700

Data Index: 27936 (C4 (Web Text))

Max Activating Token Index: 900