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

Dataset: Open Web Text

Neuron 2227 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: 1.2618. Min Range: -1.2618

Max Act: 1.2618. Min Act: -0.1263

Data Index: 1501760 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2575. Min Act: -0.0476

Data Index: 5747517 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2523. Min Act: -0.1406

Data Index: 1373375 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2296. Min Act: -0.0453

Data Index: 5747521 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2273. Min Act: -0.0609

Data Index: 881051 (Open Web Text)

Max Activating Token Index: 28

Text #5

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.2214. Min Act: -0.0917

Data Index: 5747512 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1918. Min Act: -0.1174

Data Index: 3385510 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1951. Min Act: -0.0513

Data Index: 7446267 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1976. Min Act: -0.0442

Data Index: 3454100 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1835. Min Act: -0.1253

Data Index: 294881 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1876. Min Act: -0.1260

Data Index: 8825055 (Open Web Text)

Max Activating Token Index: 51

Text #11

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1748. Min Act: -0.1096

Data Index: 2156558 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1802. Min Act: -0.1179

Data Index: 7040733 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1732. Min Act: -0.0446

Data Index: 623141 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1745. Min Act: -0.1187

Data Index: 6073397 (Open Web Text)

Max Activating Token Index: 490

Text #15

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1824. Min Act: -0.0724

Data Index: 6458023 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1748. Min Act: -0.0988

Data Index: 1605924 (Open Web Text)

Max Activating Token Index: 39

Text #17

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1692. Min Act: -0.0658

Data Index: 5014748 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1688. Min Act: -0.0797

Data Index: 2578071 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 1.2618. Min Range: -1.2618

Max Act: 1.1679. Min Act: -0.1353

Data Index: 752198 (Open Web Text)

Max Activating Token Index: 14