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

Dataset: Open Web Text

Neuron 727 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: 5.8133. Min Range: -5.8133

Max Act: 5.8133. Min Act: -0.1700

Data Index: 7224513 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.7463. Min Act: -0.1700

Data Index: 8406969 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.7004. Min Act: -0.1700

Data Index: 8819608 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6290. Min Act: -0.1700

Data Index: 234691 (Open Web Text)

Max Activating Token Index: 427

Text #4

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6394. Min Act: -0.1700

Data Index: 6756922 (Open Web Text)

Max Activating Token Index: 977

Text #5

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6112. Min Act: -0.1700

Data Index: 4715581 (Open Web Text)

Max Activating Token Index: 984

Text #6

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6345. Min Act: -0.1700

Data Index: 8201256 (Open Web Text)

Max Activating Token Index: 51

Text #7

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6448. Min Act: -0.1700

Data Index: 8821152 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6112. Min Act: -0.1700

Data Index: 6459501 (Open Web Text)

Max Activating Token Index: 273

Text #9

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5968. Min Act: -0.1700

Data Index: 1282317 (Open Web Text)

Max Activating Token Index: 327

Text #10

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6206. Min Act: -0.1700

Data Index: 1191156 (Open Web Text)

Max Activating Token Index: 704

Text #11

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.6258. Min Act: -0.1700

Data Index: 6338729 (Open Web Text)

Max Activating Token Index: 51

Text #12

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5887. Min Act: -0.1700

Data Index: 4977194 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5702. Min Act: -0.1700

Data Index: 5142967 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5645. Min Act: -0.1700

Data Index: 8096211 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5958. Min Act: -0.1700

Data Index: 7984000 (Open Web Text)

Max Activating Token Index: 769

Text #16

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5944. Min Act: -0.1700

Data Index: 7141105 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5793. Min Act: -0.1700

Data Index: 8512883 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5815. Min Act: -0.1700

Data Index: 6188007 (Open Web Text)

Max Activating Token Index: 735

Text #19

Max Range: 5.8133. Min Range: -5.8133

Max Act: 5.5711. Min Act: -0.1700

Data Index: 5730884 (Open Web Text)

Max Activating Token Index: 995