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

Dataset: Open Web Text

Neuron 585 in Layer 5

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: 4.0083. Min Range: -4.0083

Max Act: 4.0083. Min Act: -0.1700

Data Index: 1726524 (Open Web Text)

Max Activating Token Index: 383

Text #1

Max Range: 4.0083. Min Range: -4.0083

Max Act: 4.0058. Min Act: -0.1700

Data Index: 7384796 (Open Web Text)

Max Activating Token Index: 423

Text #2

Max Range: 4.0083. Min Range: -4.0083

Max Act: 4.0031. Min Act: -0.1700

Data Index: 4059118 (Open Web Text)

Max Activating Token Index: 649

Text #3

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9849. Min Act: -0.1700

Data Index: 637837 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9726. Min Act: -0.1700

Data Index: 8572508 (Open Web Text)

Max Activating Token Index: 219

Text #5

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9813. Min Act: -0.1700

Data Index: 3362800 (Open Web Text)

Max Activating Token Index: 895

Text #6

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9823. Min Act: -0.1700

Data Index: 2202136 (Open Web Text)

Max Activating Token Index: 995

Text #7

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9893. Min Act: -0.1700

Data Index: 6405153 (Open Web Text)

Max Activating Token Index: 423

Text #8

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9915. Min Act: -0.1700

Data Index: 1018796 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9465. Min Act: -0.1700

Data Index: 6031475 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9437. Min Act: -0.1700

Data Index: 2112178 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9179. Min Act: -0.1700

Data Index: 6818045 (Open Web Text)

Max Activating Token Index: 823

Text #12

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8994. Min Act: -0.1700

Data Index: 6844808 (Open Web Text)

Max Activating Token Index: 385

Text #13

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9373. Min Act: -0.1700

Data Index: 753910 (Open Web Text)

Max Activating Token Index: 626

Text #14

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9032. Min Act: -0.1700

Data Index: 892717 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.9208. Min Act: -0.1700

Data Index: 5284754 (Open Web Text)

Max Activating Token Index: 997

Text #16

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8982. Min Act: -0.1700

Data Index: 2194808 (Open Web Text)

Max Activating Token Index: 663

Text #17

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8601. Min Act: -0.1700

Data Index: 7147962 (Open Web Text)

Max Activating Token Index: 178

Text #18

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8979. Min Act: -0.1700

Data Index: 3671659 (Open Web Text)

Max Activating Token Index: 120

Text #19

Max Range: 4.0083. Min Range: -4.0083

Max Act: 3.8541. Min Act: -0.1700

Data Index: 5461274 (Open Web Text)

Max Activating Token Index: 446