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

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

Neuron 1523 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: 3.0730. Min Range: -3.0730

Max Act: 3.0256. Min Act: -0.1700

Data Index: 976626 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.0730. Min Range: -3.0730

Max Act: 3.0730. Min Act: -0.1700

Data Index: 605277 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 3.0730. Min Range: -3.0730

Max Act: 3.0256. Min Act: -0.1700

Data Index: 1270846 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9940. Min Act: -0.1700

Data Index: 135016 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9782. Min Act: -0.1700

Data Index: 1005964 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9624. Min Act: -0.1700

Data Index: 1347963 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9466. Min Act: -0.1700

Data Index: 526631 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9624. Min Act: -0.1700

Data Index: 1113564 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9149. Min Act: -0.1700

Data Index: 966990 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9307. Min Act: -0.1700

Data Index: 793336 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9149. Min Act: -0.1700

Data Index: 119411 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9149. Min Act: -0.1700

Data Index: 849885 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9466. Min Act: -0.1700

Data Index: 1041839 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9307. Min Act: -0.1700

Data Index: 529174 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9149. Min Act: -0.1700

Data Index: 520744 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9307. Min Act: -0.1700

Data Index: 856778 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.8990. Min Act: -0.1700

Data Index: 1079598 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.9149. Min Act: -0.1700

Data Index: 902614 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.8990. Min Act: -0.1700

Data Index: 912311 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.0730. Min Range: -3.0730

Max Act: 2.8990. Min Act: -0.1700

Data Index: 68229 (C4 (Web Text))

Max Activating Token Index: 104