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

Dataset: Open Web Text

Neuron 1441 in Layer 1

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: 0.8950. Min Range: -0.8950

Max Act: 0.8950. Min Act: -0.1700

Data Index: 5307648 (Open Web Text)

Max Activating Token Index: 149

Text #1

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.8914. Min Act: -0.1700

Data Index: 1576328 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7637. Min Act: -0.1700

Data Index: 1607003 (Open Web Text)

Max Activating Token Index: 142

Text #3

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7451. Min Act: -0.1700

Data Index: 6619245 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7487. Min Act: -0.1700

Data Index: 2007101 (Open Web Text)

Max Activating Token Index: 166

Text #5

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7473. Min Act: -0.1700

Data Index: 3985065 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7215. Min Act: -0.1700

Data Index: 5406427 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7364. Min Act: -0.1700

Data Index: 4993230 (Open Web Text)

Max Activating Token Index: 147

Text #8

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7223. Min Act: -0.1700

Data Index: 5050350 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7323. Min Act: -0.1700

Data Index: 8121628 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7442. Min Act: -0.1700

Data Index: 5053219 (Open Web Text)

Max Activating Token Index: 131

Text #11

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7163. Min Act: -0.1700

Data Index: 6508773 (Open Web Text)

Max Activating Token Index: 159

Text #12

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7217. Min Act: -0.1700

Data Index: 595698 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7045. Min Act: -0.1700

Data Index: 2878267 (Open Web Text)

Max Activating Token Index: 145

Text #14

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7144. Min Act: -0.1700

Data Index: 1280782 (Open Web Text)

Max Activating Token Index: 138

Text #15

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7013. Min Act: -0.1700

Data Index: 41254 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.7068. Min Act: -0.1700

Data Index: 2004486 (Open Web Text)

Max Activating Token Index: 130

Text #17

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.6995. Min Act: -0.1700

Data Index: 82988 (Open Web Text)

Max Activating Token Index: 130

Text #18

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.6863. Min Act: -0.1700

Data Index: 2783619 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 0.8950. Min Range: -0.8950

Max Act: 0.6960. Min Act: -0.1700

Data Index: 3353486 (Open Web Text)

Max Activating Token Index: 158