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

Dataset: Open Web Text

Neuron 2712 in Layer 0

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: 3.1887. Min Range: -3.1887

Max Act: 3.1887. Min Act: -0.1700

Data Index: 5231085 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1732. Min Act: -0.1700

Data Index: 296716 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1550. Min Act: -0.1700

Data Index: 2661922 (Open Web Text)

Max Activating Token Index: 166

Text #3

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1484. Min Act: -0.1700

Data Index: 5186734 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1442. Min Act: -0.1700

Data Index: 47558 (Open Web Text)

Max Activating Token Index: 62

Text #5

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1316. Min Act: -0.1700

Data Index: 1246042 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1305. Min Act: -0.1700

Data Index: 1059778 (Open Web Text)

Max Activating Token Index: 360

Text #7

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1065. Min Act: -0.1700

Data Index: 7807182 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1224. Min Act: -0.1700

Data Index: 3194831 (Open Web Text)

Max Activating Token Index: 296

Text #9

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1098. Min Act: -0.1700

Data Index: 7939641 (Open Web Text)

Max Activating Token Index: 220

Text #10

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0968. Min Act: -0.1700

Data Index: 1728929 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1042. Min Act: -0.1700

Data Index: 1660265 (Open Web Text)

Max Activating Token Index: 371

Text #12

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1054. Min Act: -0.1700

Data Index: 4972102 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0869. Min Act: -0.1700

Data Index: 7560726 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1050. Min Act: -0.1700

Data Index: 5490221 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0937. Min Act: -0.1700

Data Index: 2478512 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.1001. Min Act: -0.1700

Data Index: 773360 (Open Web Text)

Max Activating Token Index: 243

Text #17

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0728. Min Act: -0.1700

Data Index: 2512104 (Open Web Text)

Max Activating Token Index: 451

Text #18

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0952. Min Act: -0.1700

Data Index: 3879525 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 3.1887. Min Range: -3.1887

Max Act: 3.0771. Min Act: -0.1700

Data Index: 4841773 (Open Web Text)

Max Activating Token Index: 988