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

Dataset: Open Web Text

Neuron 2026 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: 4.1081. Min Range: -4.1081

Max Act: 4.1081. Min Act: -0.1700

Data Index: 5927696 (Open Web Text)

Max Activating Token Index: 90

Text #1

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0314. Min Act: -0.1700

Data Index: 1626193 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0039. Min Act: -0.1700

Data Index: 6960028 (Open Web Text)

Max Activating Token Index: 653

Text #3

Max Range: 4.1081. Min Range: -4.1081

Max Act: 4.0151. Min Act: -0.1700

Data Index: 7804797 (Open Web Text)

Max Activating Token Index: 800

Text #4

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9837. Min Act: -0.1700

Data Index: 6811774 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9681. Min Act: -0.1700

Data Index: 3392674 (Open Web Text)

Max Activating Token Index: 707

Text #6

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9691. Min Act: -0.1700

Data Index: 5578277 (Open Web Text)

Max Activating Token Index: 1000

Text #7

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9048. Min Act: -0.1700

Data Index: 1779029 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.9222. Min Act: -0.1700

Data Index: 8005065 (Open Web Text)

Max Activating Token Index: 657

Text #9

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8914. Min Act: -0.1700

Data Index: 4099178 (Open Web Text)

Max Activating Token Index: 420

Text #10

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8895. Min Act: -0.1700

Data Index: 7530240 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8580. Min Act: -0.1700

Data Index: 2325168 (Open Web Text)

Max Activating Token Index: 993

Text #12

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8776. Min Act: -0.1700

Data Index: 4856001 (Open Web Text)

Max Activating Token Index: 845

Text #13

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8415. Min Act: -0.1700

Data Index: 8813396 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8573. Min Act: -0.1700

Data Index: 7745420 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8591. Min Act: -0.1700

Data Index: 1523430 (Open Web Text)

Max Activating Token Index: 661

Text #16

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8376. Min Act: -0.1700

Data Index: 3336683 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8655. Min Act: -0.1700

Data Index: 6416166 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8296. Min Act: -0.1700

Data Index: 6232922 (Open Web Text)

Max Activating Token Index: 747

Text #19

Max Range: 4.1081. Min Range: -4.1081

Max Act: 3.8391. Min Act: -0.1700

Data Index: 3708842 (Open Web Text)

Max Activating Token Index: 982