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

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

Neuron 742 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: 3.2961. Min Range: -3.2961

Max Act: 3.2961. Min Act: -0.1700

Data Index: 1355553 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.2489. Min Act: -0.1700

Data Index: 467951 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.2018. Min Act: -0.1700

Data Index: 4567 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.2332. Min Act: -0.1700

Data Index: 1353370 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.1703. Min Act: -0.1700

Data Index: 160687 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.1230. Min Act: -0.1700

Data Index: 925785 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.1230. Min Act: -0.1700

Data Index: 1061354 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.1230. Min Act: -0.1700

Data Index: 133590 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0599. Min Act: -0.1700

Data Index: 692674 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0915. Min Act: -0.1700

Data Index: 200533 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0599. Min Act: -0.1700

Data Index: 1327870 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0599. Min Act: -0.1700

Data Index: 961104 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0757. Min Act: -0.1700

Data Index: 389647 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0757. Min Act: -0.1700

Data Index: 1249263 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0284. Min Act: -0.1700

Data Index: 499435 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0442. Min Act: -0.1700

Data Index: 1153524 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0284. Min Act: -0.1700

Data Index: 1309522 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0284. Min Act: -0.1700

Data Index: 1027482 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.0284. Min Act: -0.1700

Data Index: 780950 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.9968. Min Act: -0.1700

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 299