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

Dataset: Open Web Text

Neuron 842 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: 0.9948. Min Range: -0.9948

Max Act: 0.9948. Min Act: -0.1700

Data Index: 5895707 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9380. Min Act: -0.1700

Data Index: 8163215 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9285. Min Act: -0.1699

Data Index: 623914 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9260. Min Act: -0.1700

Data Index: 8600305 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9260. Min Act: -0.1700

Data Index: 8600284 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9260. Min Act: -0.1697

Data Index: 8600283 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9165. Min Act: -0.1700

Data Index: 7350818 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9161. Min Act: -0.1700

Data Index: 6855836 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9180. Min Act: -0.1700

Data Index: 6634095 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9161. Min Act: -0.1700

Data Index: 6256567 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9124. Min Act: -0.1700

Data Index: 446609 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9124. Min Act: -0.1700

Data Index: 8490955 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9073. Min Act: -0.1700

Data Index: 8477578 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9058. Min Act: -0.1700

Data Index: 1990749 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9058. Min Act: -0.1700

Data Index: 7761887 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9022. Min Act: -0.1700

Data Index: 4107908 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.9006. Min Act: -0.1700

Data Index: 3028608 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.8867. Min Act: -0.1700

Data Index: 1008032 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.8887. Min Act: -0.1700

Data Index: 6938874 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 0.9948. Min Range: -0.9948

Max Act: 0.8887. Min Act: -0.1700

Data Index: 24765 (Open Web Text)

Max Activating Token Index: 3