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

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

Neuron 213 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.5818. Min Act: -0.1700

Data Index: 613438 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.5818. Min Act: -0.1700

Data Index: 1230012 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.5818. Min Act: -0.1700

Data Index: 686788 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.5818. Min Act: -0.1700

Data Index: 292239 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4879. Min Act: -0.1700

Data Index: 3993 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4565. Min Act: -0.1700

Data Index: 488009 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 759450 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1017114 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 906431 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.3938. Min Act: -0.1700

Data Index: 533246 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4251. Min Act: -0.1700

Data Index: 610208 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 645138 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 901283 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1139850 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 316981 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.3938. Min Act: -0.1700

Data Index: 956785 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.3781. Min Act: -0.1700

Data Index: 103245 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.3938. Min Act: -0.1700

Data Index: 825860 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1221256 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 3.5818. Min Range: -3.5818

Max Act: 3.3938. Min Act: -0.1700

Data Index: 527383 (C4 (Web Text))

Max Activating Token Index: 214