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

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

Neuron 1576 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.2803. Min Act: -0.1700

Data Index: 143601 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.1703. Min Act: -0.1700

Data Index: 607440 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0915. Min Act: -0.1700

Data Index: 638223 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0915. Min Act: -0.1700

Data Index: 449075 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0915. Min Act: -0.1700

Data Index: 612641 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0757. Min Act: -0.1700

Data Index: 734048 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0441. Min Act: -0.1700

Data Index: 956835 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0757. Min Act: -0.1700

Data Index: 1282179 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0757. Min Act: -0.1700

Data Index: 527574 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0757. Min Act: -0.1700

Data Index: 473979 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0599. Min Act: -0.1700

Data Index: 1094034 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.9967. Min Act: -0.1700

Data Index: 1068684 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1334460 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0441. Min Act: -0.1700

Data Index: 113950 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1106146 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0125. Min Act: -0.1700

Data Index: 594177 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0283. Min Act: -0.1700

Data Index: 1235085 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.9809. Min Act: -0.1700

Data Index: 1095407 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.2803. Min Range: -3.2803

Max Act: 2.9967. Min Act: -0.1700

Data Index: 1322613 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 3.2803. Min Range: -3.2803

Max Act: 3.0125. Min Act: -0.1700

Data Index: 881222 (C4 (Web Text))

Max Activating Token Index: 29