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

Dataset: Open Web Text

Neuron 996 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: 1.7671. Min Range: -1.7671

Max Act: 1.7671. Min Act: -0.1700

Data Index: 1792521 (Open Web Text)

Max Activating Token Index: 135

Text #1

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7582. Min Act: -0.1697

Data Index: 136547 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7309. Min Act: -0.1700

Data Index: 1493962 (Open Web Text)

Max Activating Token Index: 209

Text #3

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7406. Min Act: -0.1700

Data Index: 1942283 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7379. Min Act: -0.1700

Data Index: 317165 (Open Web Text)

Max Activating Token Index: 158

Text #5

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7310. Min Act: -0.1700

Data Index: 6166693 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7137. Min Act: -0.1700

Data Index: 4129901 (Open Web Text)

Max Activating Token Index: 407

Text #7

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7252. Min Act: -0.1700

Data Index: 307073 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7270. Min Act: -0.1700

Data Index: 1007700 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7276. Min Act: -0.1700

Data Index: 3633929 (Open Web Text)

Max Activating Token Index: 38

Text #10

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7152. Min Act: -0.1699

Data Index: 4330381 (Open Web Text)

Max Activating Token Index: 905

Text #11

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7158. Min Act: -0.1700

Data Index: 254616 (Open Web Text)

Max Activating Token Index: 246

Text #12

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6987. Min Act: -0.1696

Data Index: 136545 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7037. Min Act: -0.1700

Data Index: 3541740 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.7063. Min Act: -0.1700

Data Index: 6300172 (Open Web Text)

Max Activating Token Index: 869

Text #15

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6969. Min Act: -0.1700

Data Index: 8292924 (Open Web Text)

Max Activating Token Index: 265

Text #16

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6970. Min Act: -0.1700

Data Index: 7077988 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6941. Min Act: -0.1700

Data Index: 531339 (Open Web Text)

Max Activating Token Index: 612

Text #18

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6830. Min Act: -0.1700

Data Index: 1767567 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 1.7671. Min Range: -1.7671

Max Act: 1.6911. Min Act: -0.1700

Data Index: 2326407 (Open Web Text)

Max Activating Token Index: 161