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

Dataset: Open Web Text

Neuron 136 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: 4.7518. Min Range: -4.7518

Max Act: 4.7518. Min Act: -0.1700

Data Index: 219437 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.7518. Min Act: -0.1700

Data Index: 5053164 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.6006. Min Act: -0.1700

Data Index: 5551128 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5581. Min Act: -0.1700

Data Index: 5581803 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5646. Min Act: -0.1700

Data Index: 6262359 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5554. Min Act: -0.1700

Data Index: 1285620 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5650. Min Act: -0.1700

Data Index: 2451457 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5664. Min Act: -0.1700

Data Index: 8277568 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5354. Min Act: -0.1700

Data Index: 5109961 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5392. Min Act: -0.1700

Data Index: 3772262 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5222. Min Act: -0.1700

Data Index: 2559486 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5274. Min Act: -0.1700

Data Index: 3760639 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5179. Min Act: -0.1700

Data Index: 1399844 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5231. Min Act: -0.1700

Data Index: 7146903 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5135. Min Act: -0.1700

Data Index: 2133385 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5043. Min Act: -0.1700

Data Index: 429375 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.4988. Min Act: -0.1700

Data Index: 1464522 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.4849. Min Act: -0.1700

Data Index: 760966 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.4943. Min Act: -0.1700

Data Index: 895291 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.7518. Min Range: -4.7518

Max Act: 4.5221. Min Act: -0.1700

Data Index: 943935 (Open Web Text)

Max Activating Token Index: 3