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

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

Neuron 855 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: 5.5446. Min Range: -5.5446

Max Act: 5.3571. Min Act: -0.1700

Data Index: 174284 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.5446. Min Act: -0.1700

Data Index: 382620 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.4196. Min Act: -0.1700

Data Index: 1339726 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.4821. Min Act: -0.1700

Data Index: 934795 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.4509. Min Act: -0.1700

Data Index: 59273 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3884. Min Act: -0.1700

Data Index: 868396 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3259. Min Act: -0.1700

Data Index: 1359245 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3259. Min Act: -0.1700

Data Index: 1038372 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3884. Min Act: -0.1700

Data Index: 205712 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3571. Min Act: -0.1700

Data Index: 309167 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3884. Min Act: -0.1700

Data Index: 430072 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3571. Min Act: -0.1700

Data Index: 541326 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.2946. Min Act: -0.1700

Data Index: 1159892 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3259. Min Act: -0.1700

Data Index: 377620 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3259. Min Act: -0.1700

Data Index: 599463 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3571. Min Act: -0.1700

Data Index: 62117 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.2946. Min Act: -0.1700

Data Index: 1355125 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.3259. Min Act: -0.1700

Data Index: 325433 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.2634. Min Act: -0.1700

Data Index: 770152 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 5.5446. Min Range: -5.5446

Max Act: 5.2946. Min Act: -0.1700

Data Index: 18169 (C4 (Web Text))

Max Activating Token Index: 786