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

Dataset: Open Web Text

Neuron 2476 in Layer 3

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: 3.2585. Min Range: -3.2585

Max Act: 3.2585. Min Act: -0.1700

Data Index: 4732874 (Open Web Text)

Max Activating Token Index: 997

Text #1

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0608. Min Act: -0.1700

Data Index: 7767693 (Open Web Text)

Max Activating Token Index: 170

Text #2

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0706. Min Act: -0.1700

Data Index: 7772137 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0274. Min Act: -0.1700

Data Index: 3322565 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0350. Min Act: -0.1700

Data Index: 8266802 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0397. Min Act: -0.1700

Data Index: 6585688 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0052. Min Act: -0.1700

Data Index: 5670784 (Open Web Text)

Max Activating Token Index: 639

Text #7

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0047. Min Act: -0.1700

Data Index: 7214121 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0120. Min Act: -0.1700

Data Index: 4732873 (Open Web Text)

Max Activating Token Index: 204

Text #9

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9850. Min Act: -0.1700

Data Index: 78176 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9608. Min Act: -0.1700

Data Index: 3740510 (Open Web Text)

Max Activating Token Index: 758

Text #11

Max Range: 3.2585. Min Range: -3.2585

Max Act: 3.0043. Min Act: -0.1700

Data Index: 7767692 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9805. Min Act: -0.1700

Data Index: 3481815 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9691. Min Act: -0.1700

Data Index: 2923704 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9880. Min Act: -0.1700

Data Index: 8557369 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9686. Min Act: -0.1700

Data Index: 4338972 (Open Web Text)

Max Activating Token Index: 187

Text #16

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9866. Min Act: -0.1700

Data Index: 7719106 (Open Web Text)

Max Activating Token Index: 218

Text #17

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9379. Min Act: -0.1700

Data Index: 7942548 (Open Web Text)

Max Activating Token Index: 736

Text #18

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9785. Min Act: -0.1700

Data Index: 6702069 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 3.2585. Min Range: -3.2585

Max Act: 2.9710. Min Act: -0.1700

Data Index: 4496733 (Open Web Text)

Max Activating Token Index: 30