Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1399 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.9036. Min Act: -0.1700

Data Index: 726538 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7801. Min Act: -0.1700

Data Index: 157478 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7699. Min Act: -0.1513

Data Index: 211495 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.7212. Min Act: -0.1700

Data Index: 398673 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6887. Min Act: -0.1699

Data Index: 1095447 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6902. Min Act: -0.1700

Data Index: 1089473 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6767. Min Act: -0.1700

Data Index: 100229 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6646. Min Act: -0.1700

Data Index: 488580 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6131. Min Act: -0.1700

Data Index: 1100979 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6284. Min Act: -0.1700

Data Index: 1255901 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6198. Min Act: -0.1700

Data Index: 841226 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6322. Min Act: -0.1699

Data Index: 1306555 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6070. Min Act: -0.1700

Data Index: 905360 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6029. Min Act: -0.1700

Data Index: 738048 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5978. Min Act: -0.1700

Data Index: 17556 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.6023. Min Act: -0.1700

Data Index: 800583 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5983. Min Act: -0.1660

Data Index: 120748 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5626. Min Act: -0.0696

Data Index: 398579 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5583. Min Act: -0.1700

Data Index: 296984 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 3.9036. Min Range: -3.9036

Max Act: 3.5802. Min Act: -0.1700

Data Index: 76914 (C4 (Web Text))

Max Activating Token Index: 111