Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 339 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.6974. Min Act: -0.1700

Data Index: 931592 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.5724. Min Act: -0.1700

Data Index: 974210 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.5412. Min Act: -0.1700

Data Index: 549603 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.4474. Min Act: -0.1700

Data Index: 665939 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.3849. Min Act: -0.1699

Data Index: 639819 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.4162. Min Act: -0.1699

Data Index: 247355 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.3537. Min Act: -0.1700

Data Index: 485102 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.2599. Min Act: -0.1699

Data Index: 1168450 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.3224. Min Act: -0.1700

Data Index: 1146308 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.2287. Min Act: -0.1700

Data Index: 705494 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.1037. Min Act: -0.1700

Data Index: 23658 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.1037. Min Act: -0.1700

Data Index: 1319433 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0412. Min Act: -0.1700

Data Index: 1051141 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0099. Min Act: -0.1700

Data Index: 439800 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0724. Min Act: -0.1700

Data Index: 4153 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0099. Min Act: -0.1700

Data Index: 1037518 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 7.6974. Min Range: -7.6974

Max Act: 6.9474. Min Act: -0.1700

Data Index: 842831 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 7.6974. Min Range: -7.6974

Max Act: 6.8849. Min Act: -0.1700

Data Index: 909662 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0412. Min Act: -0.1700

Data Index: 663503 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 7.6974. Min Range: -7.6974

Max Act: 7.0412. Min Act: -0.1699

Data Index: 252153 (C4 (Web Text))

Max Activating Token Index: 941