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

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

Neuron 229 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.3501. Min Act: -0.1700

Data Index: 1013827 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2876. Min Act: -0.1700

Data Index: 373004 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.3189. Min Act: -0.1700

Data Index: 732793 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.3189. Min Act: -0.1700

Data Index: 610609 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2564. Min Act: -0.1700

Data Index: 316524 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2564. Min Act: -0.1700

Data Index: 321017 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2251. Min Act: -0.1700

Data Index: 1047852 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2564. Min Act: -0.1700

Data Index: 768111 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2876. Min Act: -0.1700

Data Index: 945720 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2876. Min Act: -0.1700

Data Index: 354950 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2251. Min Act: -0.1700

Data Index: 844763 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1939. Min Act: -0.1700

Data Index: 499151 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1939. Min Act: -0.1700

Data Index: 829435 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1939. Min Act: -0.1700

Data Index: 1264148 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1626. Min Act: -0.1700

Data Index: 415167 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2251. Min Act: -0.1700

Data Index: 374235 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1314. Min Act: -0.1700

Data Index: 1353521 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.2564. Min Act: -0.1700

Data Index: 1165958 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.0689. Min Act: -0.1700

Data Index: 203050 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 5.3501. Min Range: -5.3501

Max Act: 5.1001. Min Act: -0.1700

Data Index: 591741 (C4 (Web Text))

Max Activating Token Index: 771