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

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

Neuron 1989 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: 3.2147. Min Range: -3.2147

Max Act: 3.1989. Min Act: -0.1700

Data Index: 410573 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.2147. Min Act: -0.1700

Data Index: 200803 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1989. Min Act: -0.1700

Data Index: 1040954 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1989. Min Act: -0.1700

Data Index: 384120 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1989. Min Act: -0.1700

Data Index: 672687 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1832. Min Act: -0.1700

Data Index: 1058852 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1517. Min Act: -0.1700

Data Index: 28133 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1675. Min Act: -0.1700

Data Index: 1359651 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1675. Min Act: -0.1700

Data Index: 930454 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1202. Min Act: -0.1700

Data Index: 708381 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1360. Min Act: -0.1700

Data Index: 988218 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1202. Min Act: -0.1700

Data Index: 992612 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1202. Min Act: -0.1700

Data Index: 416845 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0887. Min Act: -0.1700

Data Index: 753683 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0887. Min Act: -0.1700

Data Index: 9694 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.1045. Min Act: -0.1700

Data Index: 248596 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0887. Min Act: -0.1700

Data Index: 1290701 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0887. Min Act: -0.1700

Data Index: 301363 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0887. Min Act: -0.1700

Data Index: 68667 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.2147. Min Range: -3.2147

Max Act: 3.0729. Min Act: -0.1700

Data Index: 1328924 (C4 (Web Text))

Max Activating Token Index: 493