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

Dataset: Open Web Text

Neuron 651 in Layer 2

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: 1.9809. Min Range: -1.9809

Max Act: 1.9809. Min Act: -0.1700

Data Index: 5507884 (Open Web Text)

Max Activating Token Index: 41

Text #1

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8789. Min Act: -0.1700

Data Index: 6577934 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8742. Min Act: -0.1700

Data Index: 4759561 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8657. Min Act: -0.1700

Data Index: 7641302 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8515. Min Act: -0.1700

Data Index: 4696267 (Open Web Text)

Max Activating Token Index: 740

Text #5

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8526. Min Act: -0.1700

Data Index: 2193439 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8577. Min Act: -0.1699

Data Index: 4759557 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8559. Min Act: -0.1700

Data Index: 657064 (Open Web Text)

Max Activating Token Index: 346

Text #8

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8566. Min Act: -0.1700

Data Index: 1924632 (Open Web Text)

Max Activating Token Index: 1006

Text #9

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8563. Min Act: -0.1700

Data Index: 2201160 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8398. Min Act: -0.1700

Data Index: 7667018 (Open Web Text)

Max Activating Token Index: 169

Text #11

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8300. Min Act: -0.1700

Data Index: 6971931 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8146. Min Act: -0.1700

Data Index: 1519879 (Open Web Text)

Max Activating Token Index: 777

Text #13

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8161. Min Act: -0.1698

Data Index: 5348163 (Open Web Text)

Max Activating Token Index: 244

Text #14

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8102. Min Act: -0.1641

Data Index: 3501447 (Open Web Text)

Max Activating Token Index: 632

Text #15

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8025. Min Act: -0.1700

Data Index: 3962423 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8052. Min Act: -0.1700

Data Index: 2289935 (Open Web Text)

Max Activating Token Index: 614

Text #17

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8080. Min Act: -0.1700

Data Index: 3114781 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8030. Min Act: -0.1700

Data Index: 4826603 (Open Web Text)

Max Activating Token Index: 578

Text #19

Max Range: 1.9809. Min Range: -1.9809

Max Act: 1.8068. Min Act: -0.1700

Data Index: 5581612 (Open Web Text)

Max Activating Token Index: 213