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

Dataset: Open Web Text

Neuron 2068 in Layer 5

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: 4.3074. Min Range: -4.3074

Max Act: 4.3074. Min Act: -0.1700

Data Index: 9957 (Open Web Text)

Max Activating Token Index: 618

Text #1

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2685. Min Act: -0.1700

Data Index: 8733709 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2539. Min Act: -0.1700

Data Index: 6438946 (Open Web Text)

Max Activating Token Index: 370

Text #3

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2757. Min Act: -0.1700

Data Index: 5849926 (Open Web Text)

Max Activating Token Index: 735

Text #4

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2216. Min Act: -0.1700

Data Index: 2046291 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2322. Min Act: -0.1700

Data Index: 4541645 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2159. Min Act: -0.1700

Data Index: 7369523 (Open Web Text)

Max Activating Token Index: 670

Text #7

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.2069. Min Act: -0.1700

Data Index: 1819056 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1713. Min Act: -0.1700

Data Index: 1029180 (Open Web Text)

Max Activating Token Index: 491

Text #9

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1957. Min Act: -0.1700

Data Index: 739347 (Open Web Text)

Max Activating Token Index: 781

Text #10

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1438. Min Act: -0.1700

Data Index: 5531514 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1675. Min Act: -0.1700

Data Index: 2046307 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1757. Min Act: -0.1700

Data Index: 2184328 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1089. Min Act: -0.1700

Data Index: 1680292 (Open Web Text)

Max Activating Token Index: 414

Text #14

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1662. Min Act: -0.1700

Data Index: 6438953 (Open Web Text)

Max Activating Token Index: 815

Text #15

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1137. Min Act: -0.1700

Data Index: 2046309 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1758. Min Act: -0.1700

Data Index: 3447933 (Open Web Text)

Max Activating Token Index: 948

Text #17

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1396. Min Act: -0.1700

Data Index: 2046290 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1518. Min Act: -0.1700

Data Index: 2046310 (Open Web Text)

Max Activating Token Index: 867

Text #19

Max Range: 4.3074. Min Range: -4.3074

Max Act: 4.1120. Min Act: -0.1700

Data Index: 6438949 (Open Web Text)

Max Activating Token Index: 486