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

Dataset: Open Web Text

Neuron 1766 in Layer 4

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: 3.8597. Min Range: -3.8597

Max Act: 3.8597. Min Act: -0.1700

Data Index: 597891 (Open Web Text)

Max Activating Token Index: 956

Text #1

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7903. Min Act: -0.1700

Data Index: 6319209 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7905. Min Act: -0.1700

Data Index: 4618000 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7770. Min Act: -0.1700

Data Index: 7399390 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.8004. Min Act: -0.1700

Data Index: 7379049 (Open Web Text)

Max Activating Token Index: 497

Text #5

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7855. Min Act: -0.1700

Data Index: 651234 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7507. Min Act: -0.1700

Data Index: 2800999 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7696. Min Act: -0.1700

Data Index: 1094765 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7418. Min Act: -0.1700

Data Index: 6918514 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7668. Min Act: -0.1700

Data Index: 3452498 (Open Web Text)

Max Activating Token Index: 97

Text #10

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7408. Min Act: -0.1700

Data Index: 3856523 (Open Web Text)

Max Activating Token Index: 103

Text #11

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7462. Min Act: -0.1700

Data Index: 1051542 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7285. Min Act: -0.1700

Data Index: 4677031 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7181. Min Act: -0.1700

Data Index: 2938441 (Open Web Text)

Max Activating Token Index: 618

Text #14

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7315. Min Act: -0.1700

Data Index: 43833 (Open Web Text)

Max Activating Token Index: 86

Text #15

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7250. Min Act: -0.1700

Data Index: 2122176 (Open Web Text)

Max Activating Token Index: 423

Text #16

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.6853. Min Act: -0.1700

Data Index: 3221225 (Open Web Text)

Max Activating Token Index: 468

Text #17

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7283. Min Act: -0.1700

Data Index: 4474091 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7322. Min Act: -0.1700

Data Index: 2542277 (Open Web Text)

Max Activating Token Index: 428

Text #19

Max Range: 3.8597. Min Range: -3.8597

Max Act: 3.7329. Min Act: -0.1700

Data Index: 4621771 (Open Web Text)

Max Activating Token Index: 272