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

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

Neuron 120 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: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 127607 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 683626 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1699

Data Index: 7060 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1700

Data Index: 220082 (C4 (Web Text))

Max Activating Token Index: 856

Text #4

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1700

Data Index: 1060244 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1699

Data Index: 214541 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1699

Data Index: 860574 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1700

Data Index: 413314 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 570738 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1700

Data Index: 563926 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9354. Min Act: -0.1700

Data Index: 1095316 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9667. Min Act: -0.1700

Data Index: 891331 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1700

Data Index: 1344597 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8416. Min Act: -0.1700

Data Index: 672204 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.8729. Min Act: -0.1700

Data Index: 1069132 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1700

Data Index: 117609 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1700

Data Index: 724332 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1700

Data Index: 959801 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 3.9667. Min Range: -3.9667

Max Act: 3.9042. Min Act: -0.1700

Data Index: 447156 (C4 (Web Text))

Max Activating Token Index: 712