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

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

Neuron 295 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: 5.4155. Min Range: -5.4155

Max Act: 5.4155. Min Act: -0.1700

Data Index: 752255 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.3530. Min Act: -0.1700

Data Index: 511949 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.3530. Min Act: -0.1700

Data Index: 985279 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1655. Min Act: -0.1700

Data Index: 541600 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.2280. Min Act: -0.1700

Data Index: 1237853 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.2592. Min Act: -0.1700

Data Index: 998544 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1967. Min Act: -0.1700

Data Index: 184883 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1655. Min Act: -0.1700

Data Index: 212763 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1655. Min Act: -0.1700

Data Index: 68433 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1967. Min Act: -0.1700

Data Index: 845050 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1655. Min Act: -0.1700

Data Index: 56913 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1967. Min Act: -0.1700

Data Index: 253541 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1967. Min Act: -0.1700

Data Index: 775899 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1655. Min Act: -0.1700

Data Index: 301325 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.2280. Min Act: -0.1700

Data Index: 349854 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1030. Min Act: -0.1700

Data Index: 264245 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.0717. Min Act: -0.1700

Data Index: 1146864 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1030. Min Act: -0.1700

Data Index: 769911 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1240237 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 5.4155. Min Range: -5.4155

Max Act: 5.1342. Min Act: -0.1700

Data Index: 204400 (C4 (Web Text))

Max Activating Token Index: 87