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

Dataset: Open Web Text

Neuron 2371 in Layer 6

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: 5.5451. Min Range: -5.5451

Max Act: 5.5451. Min Act: -0.1700

Data Index: 1425724 (Open Web Text)

Max Activating Token Index: 958

Text #1

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.4875. Min Act: -0.1700

Data Index: 248102 (Open Web Text)

Max Activating Token Index: 424

Text #2

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.3805. Min Act: -0.1700

Data Index: 1186776 (Open Web Text)

Max Activating Token Index: 677

Text #3

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.4197. Min Act: -0.1700

Data Index: 3670890 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.3642. Min Act: -0.1700

Data Index: 7438956 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.2940. Min Act: -0.1700

Data Index: 6849368 (Open Web Text)

Max Activating Token Index: 26

Text #6

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1658. Min Act: -0.1700

Data Index: 123872 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1840. Min Act: -0.1700

Data Index: 2615 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.2385. Min Act: -0.1700

Data Index: 8293114 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1842. Min Act: -0.1700

Data Index: 37076 (Open Web Text)

Max Activating Token Index: 462

Text #10

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1519. Min Act: -0.1700

Data Index: 3752441 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.2004. Min Act: -0.1700

Data Index: 2499814 (Open Web Text)

Max Activating Token Index: 382

Text #12

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.2170. Min Act: -0.1700

Data Index: 7726115 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.2216. Min Act: -0.1700

Data Index: 1263060 (Open Web Text)

Max Activating Token Index: 493

Text #14

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1858. Min Act: -0.1700

Data Index: 5829127 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1368. Min Act: -0.1700

Data Index: 3572378 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1664. Min Act: -0.1700

Data Index: 7528416 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1143. Min Act: -0.1700

Data Index: 2858580 (Open Web Text)

Max Activating Token Index: 609

Text #18

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1587. Min Act: -0.1700

Data Index: 1103128 (Open Web Text)

Max Activating Token Index: 800

Text #19

Max Range: 5.5451. Min Range: -5.5451

Max Act: 5.1005. Min Act: -0.1700

Data Index: 1353626 (Open Web Text)

Max Activating Token Index: 81