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

Dataset: Open Web Text

Neuron 20 in Layer 3

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: 1.8321. Min Range: -1.8321

Max Act: 1.8321. Min Act: -0.1700

Data Index: 7673583 (Open Web Text)

Max Activating Token Index: 728

Text #1

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6942. Min Act: -0.1693

Data Index: 357086 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6792. Min Act: -0.1700

Data Index: 3915285 (Open Web Text)

Max Activating Token Index: 744

Text #3

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6479. Min Act: -0.1699

Data Index: 3022671 (Open Web Text)

Max Activating Token Index: 771

Text #4

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6511. Min Act: -0.1700

Data Index: 6971566 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6366. Min Act: -0.1697

Data Index: 7678200 (Open Web Text)

Max Activating Token Index: 73

Text #6

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6278. Min Act: -0.1700

Data Index: 3898468 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6160. Min Act: -0.1700

Data Index: 8651890 (Open Web Text)

Max Activating Token Index: 178

Text #8

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6114. Min Act: -0.1699

Data Index: 4589937 (Open Web Text)

Max Activating Token Index: 43

Text #9

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6189. Min Act: -0.1700

Data Index: 7465606 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6183. Min Act: -0.1700

Data Index: 8636869 (Open Web Text)

Max Activating Token Index: 48

Text #11

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6056. Min Act: -0.1700

Data Index: 5637798 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6032. Min Act: -0.1700

Data Index: 3016076 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6007. Min Act: -0.1700

Data Index: 7797639 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6120. Min Act: -0.1700

Data Index: 6131336 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6176. Min Act: -0.1700

Data Index: 8063990 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6036. Min Act: -0.1700

Data Index: 3543610 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6212. Min Act: -0.1700

Data Index: 4808310 (Open Web Text)

Max Activating Token Index: 205

Text #18

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.6080. Min Act: -0.1698

Data Index: 4053030 (Open Web Text)

Max Activating Token Index: 358

Text #19

Max Range: 1.8321. Min Range: -1.8321

Max Act: 1.5896. Min Act: -0.1691

Data Index: 1414492 (Open Web Text)

Max Activating Token Index: 211