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

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

Neuron 39 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0782. Min Range: -5.0782

Max Act: 5.0782. Min Act: -0.1700

Data Index: 810116 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.8907. Min Act: -0.1700

Data Index: 1272635 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.8907. Min Act: -0.1700

Data Index: 438122 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.8907. Min Act: -0.1700

Data Index: 837830 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.8594. Min Act: -0.1700

Data Index: 758488 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7969. Min Act: -0.1700

Data Index: 652403 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.8594. Min Act: -0.1700

Data Index: 708657 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7657. Min Act: -0.1700

Data Index: 1098195 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7969. Min Act: -0.1700

Data Index: 133012 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7344. Min Act: -0.1700

Data Index: 481828 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7657. Min Act: -0.1700

Data Index: 305150 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7657. Min Act: -0.1700

Data Index: 315501 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7969. Min Act: -0.1700

Data Index: 325642 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7657. Min Act: -0.1700

Data Index: 986787 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7344. Min Act: -0.1700

Data Index: 148522 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7031. Min Act: -0.1700

Data Index: 936584 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.6406. Min Act: -0.1700

Data Index: 698467 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7031. Min Act: -0.1700

Data Index: 32358 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.7031. Min Act: -0.1700

Data Index: 772612 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 5.0782. Min Range: -5.0782

Max Act: 4.6719. Min Act: -0.1700

Data Index: 1190342 (C4 (Web Text))

Max Activating Token Index: 390