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

Dataset: Open Web Text

Neuron 203 in Layer 6

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: 7.2258. Min Range: -7.2258

Max Act: 7.2258. Min Act: -0.1700

Data Index: 6708735 (Open Web Text)

Max Activating Token Index: 888

Text #1

Max Range: 7.2258. Min Range: -7.2258

Max Act: 7.1634. Min Act: -0.1700

Data Index: 5689574 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 7.2258. Min Range: -7.2258

Max Act: 7.0714. Min Act: -0.1700

Data Index: 8084117 (Open Web Text)

Max Activating Token Index: 975

Text #3

Max Range: 7.2258. Min Range: -7.2258

Max Act: 7.0455. Min Act: -0.1700

Data Index: 2876228 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9840. Min Act: -0.1700

Data Index: 5610217 (Open Web Text)

Max Activating Token Index: 623

Text #5

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9467. Min Act: -0.1700

Data Index: 3031949 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9235. Min Act: -0.1700

Data Index: 520796 (Open Web Text)

Max Activating Token Index: 270

Text #7

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9231. Min Act: -0.1700

Data Index: 2967962 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9202. Min Act: -0.1700

Data Index: 5109025 (Open Web Text)

Max Activating Token Index: 31

Text #9

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9023. Min Act: -0.1700

Data Index: 5292059 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9415. Min Act: -0.1700

Data Index: 6593881 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9003. Min Act: -0.1700

Data Index: 5064463 (Open Web Text)

Max Activating Token Index: 61

Text #12

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8855. Min Act: -0.1700

Data Index: 4344894 (Open Web Text)

Max Activating Token Index: 639

Text #13

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.9188. Min Act: -0.1700

Data Index: 242139 (Open Web Text)

Max Activating Token Index: 826

Text #14

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8685. Min Act: -0.1700

Data Index: 8133863 (Open Web Text)

Max Activating Token Index: 911

Text #15

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8839. Min Act: -0.1700

Data Index: 5600603 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8432. Min Act: -0.1700

Data Index: 5150859 (Open Web Text)

Max Activating Token Index: 930

Text #17

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8678. Min Act: -0.1700

Data Index: 2075070 (Open Web Text)

Max Activating Token Index: 147

Text #18

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8241. Min Act: -0.1700

Data Index: 7415027 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 7.2258. Min Range: -7.2258

Max Act: 6.8291. Min Act: -0.1700

Data Index: 5306577 (Open Web Text)

Max Activating Token Index: 795