Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1138 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1452. Min Act: -0.1700

Data Index: 7150410 (Open Web Text)

Max Activating Token Index: 373

Text #1

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1388. Min Act: -0.1700

Data Index: 4166744 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1142. Min Act: -0.1700

Data Index: 1633256 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1128. Min Act: -0.1700

Data Index: 5445501 (Open Web Text)

Max Activating Token Index: 428

Text #4

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1022. Min Act: -0.1700

Data Index: 646257 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0898. Min Act: -0.1700

Data Index: 1402465 (Open Web Text)

Max Activating Token Index: 447

Text #6

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1153. Min Act: -0.1700

Data Index: 3051287 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1176. Min Act: -0.1700

Data Index: 3369976 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1011. Min Act: -0.1700

Data Index: 7737818 (Open Web Text)

Max Activating Token Index: 832

Text #9

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1119. Min Act: -0.1700

Data Index: 1014101 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1021. Min Act: -0.1700

Data Index: 2986345 (Open Web Text)

Max Activating Token Index: 113

Text #11

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0984. Min Act: -0.1700

Data Index: 6980803 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1007. Min Act: -0.1700

Data Index: 8327666 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0889. Min Act: -0.1700

Data Index: 7859597 (Open Web Text)

Max Activating Token Index: 875

Text #14

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0971. Min Act: -0.1700

Data Index: 7696137 (Open Web Text)

Max Activating Token Index: 388

Text #15

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1099. Min Act: -0.1700

Data Index: 5510954 (Open Web Text)

Max Activating Token Index: 980

Text #16

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0967. Min Act: -0.1700

Data Index: 3061560 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.1048. Min Act: -0.1700

Data Index: 13172 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0655. Min Act: -0.1700

Data Index: 7124881 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 3.1452. Min Range: -3.1452

Max Act: 3.0814. Min Act: -0.1700

Data Index: 2429961 (Open Web Text)

Max Activating Token Index: 709