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

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

Neuron 1614 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1113207 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.2075. Min Act: -0.1700

Data Index: 844344 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1445. Min Act: -0.1700

Data Index: 2948 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1130. Min Act: -0.1700

Data Index: 182159 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.1130. Min Act: -0.1700

Data Index: 554487 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0972. Min Act: -0.1700

Data Index: 1152959 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0815. Min Act: -0.1700

Data Index: 226492 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0815. Min Act: -0.1700

Data Index: 154750 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0815. Min Act: -0.1700

Data Index: 320181 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0815. Min Act: -0.1700

Data Index: 1219214 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0972. Min Act: -0.1700

Data Index: 1015686 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 647336 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 1023556 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0657. Min Act: -0.1700

Data Index: 401614 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0657. Min Act: -0.1700

Data Index: 1135503 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 1188555 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0341. Min Act: -0.1700

Data Index: 123829 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 415471 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0341. Min Act: -0.1700

Data Index: 372227 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.3175. Min Range: -3.3175

Max Act: 3.0499. Min Act: -0.1700

Data Index: 606586 (C4 (Web Text))

Max Activating Token Index: 25