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

Dataset: Open Web Text

Neuron 1451 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: 6.4301. Min Range: -6.4301

Max Act: 6.4301. Min Act: -0.1700

Data Index: 4426746 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.3064. Min Act: -0.1700

Data Index: 1620635 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2701. Min Act: -0.1700

Data Index: 7425203 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2645. Min Act: -0.1700

Data Index: 1266289 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2385. Min Act: -0.1700

Data Index: 6100618 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.1839. Min Act: -0.1700

Data Index: 6511789 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2106. Min Act: -0.1700

Data Index: 1197349 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2212. Min Act: -0.1700

Data Index: 6948556 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2106. Min Act: -0.1700

Data Index: 48860 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2025. Min Act: -0.1700

Data Index: 4977110 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2032. Min Act: -0.1697

Data Index: 6804553 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2182. Min Act: -0.1700

Data Index: 1016264 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2106. Min Act: -0.1700

Data Index: 5407078 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2133. Min Act: -0.1700

Data Index: 936159 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2066. Min Act: -0.1700

Data Index: 5899066 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2039. Min Act: -0.1700

Data Index: 1230284 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.1839. Min Act: -0.1700

Data Index: 39503 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2067. Min Act: -0.1700

Data Index: 540118 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2042. Min Act: -0.1700

Data Index: 497457 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 6.4301. Min Range: -6.4301

Max Act: 6.2070. Min Act: -0.1700

Data Index: 475956 (Open Web Text)

Max Activating Token Index: 6