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

Dataset: Open Web Text

Neuron 2885 in Layer 2

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: 4.0674. Min Range: -4.0674

Max Act: 4.0674. Min Act: -0.1700

Data Index: 6837094 (Open Web Text)

Max Activating Token Index: 299

Text #1

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8848. Min Act: -0.1700

Data Index: 4914522 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.9043. Min Act: -0.1700

Data Index: 1361655 (Open Web Text)

Max Activating Token Index: 493

Text #3

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.9066. Min Act: -0.1700

Data Index: 289452 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8837. Min Act: -0.1700

Data Index: 1465829 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8499. Min Act: -0.1700

Data Index: 5041802 (Open Web Text)

Max Activating Token Index: 886

Text #6

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8663. Min Act: -0.1700

Data Index: 7487952 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8782. Min Act: -0.1700

Data Index: 1639515 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8430. Min Act: -0.1700

Data Index: 3633293 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8375. Min Act: -0.1700

Data Index: 7161281 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8451. Min Act: -0.1700

Data Index: 6908320 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8161. Min Act: -0.1700

Data Index: 4610593 (Open Web Text)

Max Activating Token Index: 141

Text #12

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8110. Min Act: -0.1700

Data Index: 3627929 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8302. Min Act: -0.1700

Data Index: 8511760 (Open Web Text)

Max Activating Token Index: 1019

Text #14

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8249. Min Act: -0.1700

Data Index: 317405 (Open Web Text)

Max Activating Token Index: 125

Text #15

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8263. Min Act: -0.1700

Data Index: 1623230 (Open Web Text)

Max Activating Token Index: 391

Text #16

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8351. Min Act: -0.1700

Data Index: 5341857 (Open Web Text)

Max Activating Token Index: 990

Text #17

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8448. Min Act: -0.1700

Data Index: 3974940 (Open Web Text)

Max Activating Token Index: 552

Text #18

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.8090. Min Act: -0.1700

Data Index: 2757269 (Open Web Text)

Max Activating Token Index: 925

Text #19

Max Range: 4.0674. Min Range: -4.0674

Max Act: 3.7867. Min Act: -0.1700

Data Index: 3518267 (Open Web Text)

Max Activating Token Index: 597