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

Dataset: Open Web Text

Neuron 2981 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: 1.0621. Min Range: -1.0621

Max Act: 1.0575. Min Act: -0.1700

Data Index: 1438101 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0621. Min Act: -0.1700

Data Index: 6213836 (Open Web Text)

Max Activating Token Index: 37

Text #2

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0253. Min Act: -0.1700

Data Index: 1668097 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0281. Min Act: -0.1700

Data Index: 3366593 (Open Web Text)

Max Activating Token Index: 36

Text #4

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0295. Min Act: -0.1700

Data Index: 6921736 (Open Web Text)

Max Activating Token Index: 42

Text #5

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0267. Min Act: -0.1700

Data Index: 6367111 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0195. Min Act: -0.1700

Data Index: 8804598 (Open Web Text)

Max Activating Token Index: 36

Text #7

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0164. Min Act: -0.1700

Data Index: 7536154 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0158. Min Act: -0.1700

Data Index: 2640271 (Open Web Text)

Max Activating Token Index: 35

Text #9

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0156. Min Act: -0.1700

Data Index: 7404404 (Open Web Text)

Max Activating Token Index: 36

Text #10

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0189. Min Act: -0.1700

Data Index: 1313077 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0164. Min Act: -0.1700

Data Index: 3847501 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0149. Min Act: -0.1700

Data Index: 547202 (Open Web Text)

Max Activating Token Index: 42

Text #13

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0089. Min Act: -0.1700

Data Index: 1100375 (Open Web Text)

Max Activating Token Index: 40

Text #14

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0146. Min Act: -0.1700

Data Index: 5490226 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0054. Min Act: -0.1700

Data Index: 546037 (Open Web Text)

Max Activating Token Index: 39

Text #16

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0091. Min Act: -0.1700

Data Index: 1159550 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0105. Min Act: -0.1700

Data Index: 4415616 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 1.0621. Min Range: -1.0621

Max Act: 1.0064. Min Act: -0.1700

Data Index: 1388361 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 1.0621. Min Range: -1.0621

Max Act: 0.9973. Min Act: -0.1700

Data Index: 3655223 (Open Web Text)

Max Activating Token Index: 32