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

Dataset: Open Web Text

Neuron 970 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: 4.4227. Min Range: -4.4227

Max Act: 4.4227. Min Act: -0.1700

Data Index: 5668659 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2097. Min Act: -0.1700

Data Index: 2775339 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2165. Min Act: -0.1700

Data Index: 7419469 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2170. Min Act: -0.1700

Data Index: 2918994 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.2202. Min Act: -0.1700

Data Index: 4985680 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1938. Min Act: -0.1700

Data Index: 5266536 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1823. Min Act: -0.1700

Data Index: 4744547 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1358. Min Act: -0.1700

Data Index: 1405433 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1241. Min Act: -0.1700

Data Index: 258251 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1487. Min Act: -0.1700

Data Index: 6982121 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1043. Min Act: -0.1700

Data Index: 1373753 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0995. Min Act: -0.1700

Data Index: 2775352 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0778. Min Act: -0.1700

Data Index: 939930 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0833. Min Act: -0.1700

Data Index: 6483184 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0761. Min Act: -0.1700

Data Index: 2775342 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0737. Min Act: -0.1700

Data Index: 2775345 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.1002. Min Act: -0.1700

Data Index: 7443938 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0860. Min Act: -0.1700

Data Index: 2775347 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0900. Min Act: -0.1700

Data Index: 8316887 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.4227. Min Range: -4.4227

Max Act: 4.0806. Min Act: -0.1700

Data Index: 5668660 (Open Web Text)

Max Activating Token Index: 74