Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 974 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2869. Min Act: -0.1700

Data Index: 919649 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.3026. Min Act: -0.1700

Data Index: 268409 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2869. Min Act: -0.1700

Data Index: 211621 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2869. Min Act: -0.1700

Data Index: 607731 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2398. Min Act: -0.1700

Data Index: 291772 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2240. Min Act: -0.1700

Data Index: 48341 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2240. Min Act: -0.1700

Data Index: 848793 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2083. Min Act: -0.1700

Data Index: 559275 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.2083. Min Act: -0.1700

Data Index: 376857 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.1926. Min Act: -0.1700

Data Index: 463997 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.1768. Min Act: -0.1700

Data Index: 930498 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.1768. Min Act: -0.1700

Data Index: 938607 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.1768. Min Act: -0.1700

Data Index: 1074888 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.1138. Min Act: -0.1700

Data Index: 1605314 (Python Code)

Max Activating Token Index: 818

Text #14

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0981. Min Act: -0.1700

Data Index: 724009 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1540936 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1048386 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0665. Min Act: -0.1700

Data Index: 506698 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0665. Min Act: -0.1700

Data Index: 1443381 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 3.3026. Min Range: -3.3026

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1555620 (Python Code)

Max Activating Token Index: 648