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

Dataset: Open Web Text

Neuron 1618 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: 3.2823. Min Range: -3.2823

Max Act: 3.2823. Min Act: -0.1700

Data Index: 5637047 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2512. Min Act: -0.1700

Data Index: 8402934 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.2158. Min Act: -0.1700

Data Index: 5779168 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1974. Min Act: -0.1700

Data Index: 688566 (Open Web Text)

Max Activating Token Index: 142

Text #4

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1858. Min Act: -0.1700

Data Index: 6097289 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1942. Min Act: -0.1700

Data Index: 3858713 (Open Web Text)

Max Activating Token Index: 213

Text #6

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1768. Min Act: -0.1700

Data Index: 3751509 (Open Web Text)

Max Activating Token Index: 302

Text #7

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1855. Min Act: -0.1700

Data Index: 274121 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1494. Min Act: -0.1700

Data Index: 3660251 (Open Web Text)

Max Activating Token Index: 630

Text #9

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1130. Min Act: -0.1700

Data Index: 3369594 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1196. Min Act: -0.1700

Data Index: 5955366 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1116. Min Act: -0.1700

Data Index: 1490099 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1046. Min Act: -0.1700

Data Index: 8114213 (Open Web Text)

Max Activating Token Index: 455

Text #13

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.1081. Min Act: -0.1700

Data Index: 5779167 (Open Web Text)

Max Activating Token Index: 1002

Text #14

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0815. Min Act: -0.1700

Data Index: 4532899 (Open Web Text)

Max Activating Token Index: 288

Text #15

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0951. Min Act: -0.1700

Data Index: 5808064 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0891. Min Act: -0.1700

Data Index: 5527453 (Open Web Text)

Max Activating Token Index: 602

Text #17

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0923. Min Act: -0.1700

Data Index: 212757 (Open Web Text)

Max Activating Token Index: 482

Text #18

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0765. Min Act: -0.1700

Data Index: 351641 (Open Web Text)

Max Activating Token Index: 95

Text #19

Max Range: 3.2823. Min Range: -3.2823

Max Act: 3.0596. Min Act: -0.1700

Data Index: 2391964 (Open Web Text)

Max Activating Token Index: 273