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

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

Neuron 1891 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0048. Min Range: -5.0048

Max Act: 5.0048. Min Act: -0.1700

Data Index: 695258 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9735. Min Act: -0.1700

Data Index: 1000032 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9423. Min Act: -0.1699

Data Index: 378217 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9735. Min Act: -0.1700

Data Index: 326497 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9735. Min Act: -0.1700

Data Index: 511026 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9735. Min Act: -0.1700

Data Index: 399155 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9735. Min Act: -0.1700

Data Index: 318187 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1021771 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9423. Min Act: -0.1700

Data Index: 359844 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.8798. Min Act: -0.1700

Data Index: 1200262 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9423. Min Act: -0.1700

Data Index: 615849 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9110. Min Act: -0.1700

Data Index: 13386 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9423. Min Act: -0.1700

Data Index: 896359 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1273650 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.8485. Min Act: -0.1700

Data Index: 788529 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.8173. Min Act: -0.1700

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9110. Min Act: -0.1700

Data Index: 47948 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.8485. Min Act: -0.1700

Data Index: 957544 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.9110. Min Act: -0.1700

Data Index: 1086565 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 5.0048. Min Range: -5.0048

Max Act: 4.8173. Min Act: -0.1700

Data Index: 625048 (C4 (Web Text))

Max Activating Token Index: 834