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

Dataset: Open Web Text

Neuron 2650 in Layer 0

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: 3.9319. Min Range: -3.9319

Max Act: 3.9319. Min Act: -0.1700

Data Index: 7572090 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8809. Min Act: -0.1700

Data Index: 1860456 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.9131. Min Act: -0.1700

Data Index: 1546746 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8564. Min Act: -0.1700

Data Index: 5010254 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8258. Min Act: -0.1700

Data Index: 5670988 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8368. Min Act: -0.1700

Data Index: 6694497 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8214. Min Act: -0.1700

Data Index: 599199 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8388. Min Act: -0.1700

Data Index: 6802894 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8390. Min Act: -0.1700

Data Index: 8802093 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8070. Min Act: -0.1700

Data Index: 823669 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8185. Min Act: -0.1700

Data Index: 564475 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8073. Min Act: -0.1700

Data Index: 3818940 (Open Web Text)

Max Activating Token Index: 88

Text #12

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.7906. Min Act: -0.1700

Data Index: 2753075 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.7911. Min Act: -0.1700

Data Index: 7566493 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8107. Min Act: -0.1700

Data Index: 7489963 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8130. Min Act: -0.1700

Data Index: 6737347 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.8036. Min Act: -0.1700

Data Index: 5384896 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.7549. Min Act: -0.1700

Data Index: 1260863 (Open Web Text)

Max Activating Token Index: 211

Text #18

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.7549. Min Act: -0.1700

Data Index: 3862619 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 3.9319. Min Range: -3.9319

Max Act: 3.7724. Min Act: -0.1700

Data Index: 4747215 (Open Web Text)

Max Activating Token Index: 57