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

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

Neuron 140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4469. Min Act: -0.1700

Data Index: 1030122 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4782. Min Act: -0.1700

Data Index: 984966 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4782. Min Act: -0.1700

Data Index: 1244008 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4469. Min Act: -0.1700

Data Index: 672596 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4157. Min Act: -0.1700

Data Index: 235259 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.3219. Min Act: -0.1700

Data Index: 518382 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.3219. Min Act: -0.1700

Data Index: 620132 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.3219. Min Act: -0.1700

Data Index: 32448 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2594. Min Act: -0.1700

Data Index: 298835 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.4157. Min Act: -0.1700

Data Index: 792202 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.3219. Min Act: -0.1700

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2594. Min Act: -0.1700

Data Index: 1292155 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2594. Min Act: -0.1700

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2907. Min Act: -0.1700

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2282. Min Act: -0.1700

Data Index: 742233 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.3532. Min Act: -0.1700

Data Index: 15812 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2594. Min Act: -0.1700

Data Index: 150923 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.1657. Min Act: -0.1700

Data Index: 584642 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.1813. Min Act: -0.1700

Data Index: 735243 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 5.4782. Min Range: -5.4782

Max Act: 5.2282. Min Act: -0.1700

Data Index: 366775 (C4 (Web Text))

Max Activating Token Index: 998