Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1736 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.6549. Min Act: -0.1700

Data Index: 119283 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.5922. Min Act: -0.1700

Data Index: 113979 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.5609. Min Act: -0.1700

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.5296. Min Act: -0.1700

Data Index: 626467 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.5296. Min Act: -0.1700

Data Index: 464766 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4669. Min Act: -0.1700

Data Index: 400213 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4669. Min Act: -0.1700

Data Index: 610861 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4983. Min Act: -0.1700

Data Index: 223652 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4983. Min Act: -0.1700

Data Index: 677414 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4983. Min Act: -0.1700

Data Index: 175375 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4669. Min Act: -0.1700

Data Index: 1349822 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1575176 (Python Code)

Max Activating Token Index: 627

Text #12

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 239291 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4356. Min Act: -0.1700

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4669. Min Act: -0.1700

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 587116 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 427155 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 885260 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.3728. Min Act: -0.1700

Data Index: 948358 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.6549. Min Range: -3.6549

Max Act: 3.4042. Min Act: -0.1700

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 283