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

Dataset: Open Web Text

Neuron 1528 in Layer 1

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: 1.6922. Min Range: -1.6922

Max Act: 1.6922. Min Act: -0.1700

Data Index: 3375608 (Open Web Text)

Max Activating Token Index: 201

Text #1

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6823. Min Act: -0.1698

Data Index: 6686829 (Open Web Text)

Max Activating Token Index: 112

Text #2

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6468. Min Act: -0.1699

Data Index: 4020932 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6404. Min Act: -0.1700

Data Index: 2979754 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6391. Min Act: -0.1700

Data Index: 6093771 (Open Web Text)

Max Activating Token Index: 181

Text #5

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6467. Min Act: -0.1700

Data Index: 3429482 (Open Web Text)

Max Activating Token Index: 122

Text #6

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6427. Min Act: -0.1700

Data Index: 2074194 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6360. Min Act: -0.1700

Data Index: 8451141 (Open Web Text)

Max Activating Token Index: 403

Text #8

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6371. Min Act: -0.1700

Data Index: 2837526 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6251. Min Act: -0.1700

Data Index: 8154411 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6185. Min Act: -0.1699

Data Index: 1227125 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6208. Min Act: -0.1699

Data Index: 2025723 (Open Web Text)

Max Activating Token Index: 121

Text #12

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6294. Min Act: -0.1419

Data Index: 3777690 (Open Web Text)

Max Activating Token Index: 670

Text #13

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6152. Min Act: -0.1700

Data Index: 8227565 (Open Web Text)

Max Activating Token Index: 278

Text #14

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6084. Min Act: -0.1700

Data Index: 5909327 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6128. Min Act: -0.1700

Data Index: 2188043 (Open Web Text)

Max Activating Token Index: 663

Text #16

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6082. Min Act: -0.1697

Data Index: 5703314 (Open Web Text)

Max Activating Token Index: 356

Text #17

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6148. Min Act: -0.1658

Data Index: 1313937 (Open Web Text)

Max Activating Token Index: 559

Text #18

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6003. Min Act: -0.1700

Data Index: 575705 (Open Web Text)

Max Activating Token Index: 208

Text #19

Max Range: 1.6922. Min Range: -1.6922

Max Act: 1.6010. Min Act: -0.1700

Data Index: 7199986 (Open Web Text)

Max Activating Token Index: 523