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

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

Neuron 1691 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: 5.4980. Min Range: -5.4980

Max Act: 5.4668. Min Act: -0.1700

Data Index: 642523 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4980. Min Act: -0.1700

Data Index: 617785 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4512. Min Act: -0.1700

Data Index: 1239624 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4824. Min Act: -0.1700

Data Index: 1217417 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4355. Min Act: -0.1700

Data Index: 9187 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4043. Min Act: -0.1700

Data Index: 589494 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.4043. Min Act: -0.1700

Data Index: 282121 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.3887. Min Act: -0.1700

Data Index: 276982 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.3730. Min Act: -0.1700

Data Index: 257767 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.3574. Min Act: -0.1700

Data Index: 1230020 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2949. Min Act: -0.1700

Data Index: 1309756 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2949. Min Act: -0.1700

Data Index: 348166 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2949. Min Act: -0.1700

Data Index: 914837 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2949. Min Act: -0.1700

Data Index: 376285 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.3418. Min Act: -0.1700

Data Index: 504712 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2949. Min Act: -0.1700

Data Index: 126536 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2793. Min Act: -0.1700

Data Index: 1099857 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.3574. Min Act: -0.1700

Data Index: 711926 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2793. Min Act: -0.1700

Data Index: 493472 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 5.4980. Min Range: -5.4980

Max Act: 5.2637. Min Act: -0.1700

Data Index: 1138946 (C4 (Web Text))

Max Activating Token Index: 739