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

Dataset: Open Web Text

Neuron 236 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: 5.9195. Min Range: -5.9195

Max Act: 5.9195. Min Act: -0.1700

Data Index: 2436987 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.9038. Min Act: -0.1700

Data Index: 1437168 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8898. Min Act: -0.1700

Data Index: 3950144 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8775. Min Act: -0.1700

Data Index: 7531890 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8677. Min Act: -0.1700

Data Index: 8799345 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8575. Min Act: -0.1700

Data Index: 7299013 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8729. Min Act: -0.1700

Data Index: 2138299 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8557. Min Act: -0.1700

Data Index: 970520 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8426. Min Act: -0.1700

Data Index: 448649 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8321. Min Act: -0.1700

Data Index: 5994324 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8103. Min Act: -0.1700

Data Index: 6735856 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8157. Min Act: -0.1700

Data Index: 7131888 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.7977. Min Act: -0.1700

Data Index: 4990347 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8312. Min Act: -0.1700

Data Index: 660214 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8313. Min Act: -0.1700

Data Index: 5847097 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.7971. Min Act: -0.1700

Data Index: 1018847 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8269. Min Act: -0.1700

Data Index: 74453 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8149. Min Act: -0.1700

Data Index: 2008300 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8034. Min Act: -0.1700

Data Index: 1022990 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.9195. Min Range: -5.9195

Max Act: 5.8115. Min Act: -0.1700

Data Index: 270024 (Open Web Text)

Max Activating Token Index: 3