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

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

Neuron 1259 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: 5.4217. Min Range: -5.4217

Max Act: 5.4217. Min Act: -0.1700

Data Index: 104838 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.2654. Min Act: -0.1700

Data Index: 1001857 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.2654. Min Act: -0.1700

Data Index: 40991 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.2029. Min Act: -0.1700

Data Index: 126613 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.2029. Min Act: -0.1700

Data Index: 1230790 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1717. Min Act: -0.1700

Data Index: 212168 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1404. Min Act: -0.1700

Data Index: 310284 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1404. Min Act: -0.1700

Data Index: 381506 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1092. Min Act: -0.1700

Data Index: 858449 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1092. Min Act: -0.1700

Data Index: 836544 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1404. Min Act: -0.1700

Data Index: 470358 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.1092. Min Act: -0.1700

Data Index: 1045586 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0779. Min Act: -0.1700

Data Index: 814796 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0779. Min Act: -0.1700

Data Index: 196294 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0154. Min Act: -0.1700

Data Index: 859718 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0467. Min Act: -0.1700

Data Index: 803129 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0467. Min Act: -0.1700

Data Index: 741754 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0467. Min Act: -0.1700

Data Index: 473269 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0154. Min Act: -0.1700

Data Index: 839962 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 5.4217. Min Range: -5.4217

Max Act: 5.0154. Min Act: -0.1700

Data Index: 1073942 (C4 (Web Text))

Max Activating Token Index: 768