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

Dataset: Open Web Text

Neuron 1652 in Layer 1

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: 1.7358. Min Range: -1.7358

Max Act: 1.7358. Min Act: -0.1700

Data Index: 7688957 (Open Web Text)

Max Activating Token Index: 395

Text #1

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6420. Min Act: -0.1700

Data Index: 7340402 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6281. Min Act: -0.1700

Data Index: 6029207 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6238. Min Act: -0.1700

Data Index: 2401216 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6208. Min Act: -0.1699

Data Index: 6525003 (Open Web Text)

Max Activating Token Index: 410

Text #5

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6224. Min Act: -0.1700

Data Index: 3152026 (Open Web Text)

Max Activating Token Index: 64

Text #6

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6261. Min Act: -0.1700

Data Index: 145427 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6184. Min Act: -0.1700

Data Index: 973298 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6135. Min Act: -0.1700

Data Index: 4583871 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6082. Min Act: -0.1699

Data Index: 6112284 (Open Web Text)

Max Activating Token Index: 52

Text #10

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6102. Min Act: -0.1700

Data Index: 3911866 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6084. Min Act: -0.1700

Data Index: 5030994 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5968. Min Act: -0.1700

Data Index: 2104330 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6029. Min Act: -0.1700

Data Index: 6183672 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6008. Min Act: -0.1700

Data Index: 1356198 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.6017. Min Act: -0.1700

Data Index: 5153762 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5939. Min Act: -0.1700

Data Index: 3649102 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5935. Min Act: -0.1700

Data Index: 4198076 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5952. Min Act: -0.1700

Data Index: 5492716 (Open Web Text)

Max Activating Token Index: 76

Text #19

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5958. Min Act: -0.1700

Data Index: 6996655 (Open Web Text)

Max Activating Token Index: 6