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

Dataset: Open Web Text

Neuron 653 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: 4.1148. Min Range: -4.1148

Max Act: 4.1148. Min Act: -0.1700

Data Index: 381705 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 4.1148. Min Range: -4.1148

Max Act: 4.0586. Min Act: -0.1700

Data Index: 836278 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 4.1148. Min Range: -4.1148

Max Act: 4.0192. Min Act: -0.1700

Data Index: 5518805 (Open Web Text)

Max Activating Token Index: 684

Text #3

Max Range: 4.1148. Min Range: -4.1148

Max Act: 4.0262. Min Act: -0.1700

Data Index: 2676091 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9841. Min Act: -0.1700

Data Index: 4077607 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9676. Min Act: -0.1700

Data Index: 3102970 (Open Web Text)

Max Activating Token Index: 387

Text #6

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9413. Min Act: -0.1700

Data Index: 3217412 (Open Web Text)

Max Activating Token Index: 133

Text #7

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9438. Min Act: -0.1700

Data Index: 7761643 (Open Web Text)

Max Activating Token Index: 222

Text #8

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9061. Min Act: -0.1700

Data Index: 8624254 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9188. Min Act: -0.1700

Data Index: 3753215 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9151. Min Act: -0.1700

Data Index: 835235 (Open Web Text)

Max Activating Token Index: 791

Text #11

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9185. Min Act: -0.1700

Data Index: 1754216 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8929. Min Act: -0.1700

Data Index: 1020810 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.9009. Min Act: -0.1700

Data Index: 2700898 (Open Web Text)

Max Activating Token Index: 175

Text #14

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8808. Min Act: -0.1700

Data Index: 1724298 (Open Web Text)

Max Activating Token Index: 841

Text #15

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8788. Min Act: -0.1700

Data Index: 7164941 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8852. Min Act: -0.1700

Data Index: 6609907 (Open Web Text)

Max Activating Token Index: 855

Text #17

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8670. Min Act: -0.1700

Data Index: 6281752 (Open Web Text)

Max Activating Token Index: 147

Text #18

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8736. Min Act: -0.1700

Data Index: 5788454 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 4.1148. Min Range: -4.1148

Max Act: 3.8874. Min Act: -0.1700

Data Index: 5562893 (Open Web Text)

Max Activating Token Index: 954