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

Dataset: Open Web Text

Neuron 1837 in Layer 4

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: 3.7068. Min Range: -3.7068

Max Act: 3.7068. Min Act: -0.1700

Data Index: 4197922 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6375. Min Act: -0.1700

Data Index: 8665395 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6154. Min Act: -0.1700

Data Index: 3166726 (Open Web Text)

Max Activating Token Index: 255

Text #3

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5946. Min Act: -0.1700

Data Index: 7259082 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5739. Min Act: -0.1700

Data Index: 907112 (Open Web Text)

Max Activating Token Index: 676

Text #5

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.6177. Min Act: -0.1700

Data Index: 922156 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5744. Min Act: -0.1700

Data Index: 2517682 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5884. Min Act: -0.1700

Data Index: 920025 (Open Web Text)

Max Activating Token Index: 906

Text #8

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5789. Min Act: -0.1700

Data Index: 8066125 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5759. Min Act: -0.1700

Data Index: 4554594 (Open Web Text)

Max Activating Token Index: 360

Text #10

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5755. Min Act: -0.1700

Data Index: 8089800 (Open Web Text)

Max Activating Token Index: 455

Text #11

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5584. Min Act: -0.1700

Data Index: 6873144 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5793. Min Act: -0.1700

Data Index: 8399835 (Open Web Text)

Max Activating Token Index: 907

Text #13

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5504. Min Act: -0.1700

Data Index: 5440240 (Open Web Text)

Max Activating Token Index: 67

Text #14

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5660. Min Act: -0.1700

Data Index: 7068779 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5584. Min Act: -0.1700

Data Index: 4573263 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5396. Min Act: -0.1700

Data Index: 2699337 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5453. Min Act: -0.1700

Data Index: 7750313 (Open Web Text)

Max Activating Token Index: 785

Text #18

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5466. Min Act: -0.1700

Data Index: 619952 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 3.7068. Min Range: -3.7068

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1226755 (Open Web Text)

Max Activating Token Index: 563