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

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

Neuron 517 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: 5.4724. Min Range: -5.4724

Max Act: 5.4724. Min Act: -0.1700

Data Index: 687184 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.4412. Min Act: -0.1700

Data Index: 187103 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3787. Min Act: -0.1700

Data Index: 1185622 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3787. Min Act: -0.1700

Data Index: 27990 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.4099. Min Act: -0.1700

Data Index: 239799 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3787. Min Act: -0.1700

Data Index: 905059 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3787. Min Act: -0.1700

Data Index: 1007961 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3787. Min Act: -0.1700

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3474. Min Act: -0.1700

Data Index: 712770 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3474. Min Act: -0.1700

Data Index: 644403 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.3474. Min Act: -0.1700

Data Index: 1356599 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2849. Min Act: -0.1700

Data Index: 445346 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2537. Min Act: -0.1700

Data Index: 103156 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2537. Min Act: -0.1700

Data Index: 634131 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2849. Min Act: -0.1700

Data Index: 80763 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2849. Min Act: -0.1700

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2224. Min Act: -0.1700

Data Index: 806163 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2849. Min Act: -0.1700

Data Index: 1161954 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2224. Min Act: -0.1700

Data Index: 503150 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 5.4724. Min Range: -5.4724

Max Act: 5.2537. Min Act: -0.1700

Data Index: 1111824 (C4 (Web Text))

Max Activating Token Index: 217