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

Dataset: Open Web Text

Neuron 2004 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: 5.0457. Min Range: -5.0457

Max Act: 5.0457. Min Act: -0.1700

Data Index: 1532007 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 5.0457. Min Range: -5.0457

Max Act: 5.0127. Min Act: -0.1700

Data Index: 894066 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 5.0457. Min Range: -5.0457

Max Act: 5.0000. Min Act: -0.1700

Data Index: 2173871 (Open Web Text)

Max Activating Token Index: 457

Text #3

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9796. Min Act: -0.1700

Data Index: 8204595 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9431. Min Act: -0.1700

Data Index: 803924 (Open Web Text)

Max Activating Token Index: 305

Text #5

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9582. Min Act: -0.1700

Data Index: 1924751 (Open Web Text)

Max Activating Token Index: 39

Text #6

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9477. Min Act: -0.1700

Data Index: 2953134 (Open Web Text)

Max Activating Token Index: 209

Text #7

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9245. Min Act: -0.1700

Data Index: 6584297 (Open Web Text)

Max Activating Token Index: 249

Text #8

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9577. Min Act: -0.1700

Data Index: 4521845 (Open Web Text)

Max Activating Token Index: 432

Text #9

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9479. Min Act: -0.1700

Data Index: 4649634 (Open Web Text)

Max Activating Token Index: 343

Text #10

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9113. Min Act: -0.1700

Data Index: 7867685 (Open Web Text)

Max Activating Token Index: 968

Text #11

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8776. Min Act: -0.1700

Data Index: 422999 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9159. Min Act: -0.1700

Data Index: 1327158 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8835. Min Act: -0.1700

Data Index: 8823625 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8713. Min Act: -0.1700

Data Index: 5582465 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8833. Min Act: -0.1700

Data Index: 3125899 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.9120. Min Act: -0.1700

Data Index: 388461 (Open Web Text)

Max Activating Token Index: 673

Text #17

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8637. Min Act: -0.1700

Data Index: 4907731 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8420. Min Act: -0.1700

Data Index: 5037129 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 5.0457. Min Range: -5.0457

Max Act: 4.8488. Min Act: -0.1700

Data Index: 5298999 (Open Web Text)

Max Activating Token Index: 270