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

Dataset: Open Web Text

Neuron 853 in Layer 6

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: 5.4806. Min Range: -5.4806

Max Act: 5.4517. Min Act: -0.1700

Data Index: 5129810 (Open Web Text)

Max Activating Token Index: 404

Text #1

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.4806. Min Act: -0.1700

Data Index: 2932827 (Open Web Text)

Max Activating Token Index: 489

Text #2

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.3443. Min Act: -0.1700

Data Index: 568384 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.2027. Min Act: -0.1700

Data Index: 6598395 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.2082. Min Act: -0.1700

Data Index: 4693572 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.1579. Min Act: -0.1700

Data Index: 5586345 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.0951. Min Act: -0.1700

Data Index: 3228957 (Open Web Text)

Max Activating Token Index: 909

Text #7

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.1106. Min Act: -0.1700

Data Index: 4628630 (Open Web Text)

Max Activating Token Index: 227

Text #8

Max Range: 5.4806. Min Range: -5.4806

Max Act: 5.0020. Min Act: -0.1700

Data Index: 8069395 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.9555. Min Act: -0.1700

Data Index: 8719708 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.9313. Min Act: -0.1700

Data Index: 7740853 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.9277. Min Act: -0.1700

Data Index: 6749370 (Open Web Text)

Max Activating Token Index: 749

Text #12

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8843. Min Act: -0.1700

Data Index: 5752661 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.9209. Min Act: -0.1700

Data Index: 5869315 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8915. Min Act: -0.1700

Data Index: 7980404 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8772. Min Act: -0.1700

Data Index: 5740360 (Open Web Text)

Max Activating Token Index: 731

Text #16

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8796. Min Act: -0.1700

Data Index: 4313811 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.9026. Min Act: -0.1700

Data Index: 5285948 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8119. Min Act: -0.1700

Data Index: 4448047 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 5.4806. Min Range: -5.4806

Max Act: 4.8396. Min Act: -0.1700

Data Index: 6362000 (Open Web Text)

Max Activating Token Index: 256