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

Dataset: Open Web Text

Neuron 2412 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: 5.0167. Min Range: -5.0167

Max Act: 5.0167. Min Act: -0.1700

Data Index: 7334406 (Open Web Text)

Max Activating Token Index: 755

Text #1

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.7816. Min Act: -0.1700

Data Index: 1554573 (Open Web Text)

Max Activating Token Index: 805

Text #2

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.7573. Min Act: -0.1700

Data Index: 7776202 (Open Web Text)

Max Activating Token Index: 173

Text #3

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6808. Min Act: -0.1700

Data Index: 5063787 (Open Web Text)

Max Activating Token Index: 670

Text #4

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.7235. Min Act: -0.1700

Data Index: 3665023 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6710. Min Act: -0.1700

Data Index: 3593605 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6414. Min Act: -0.1700

Data Index: 261663 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6048. Min Act: -0.1700

Data Index: 8051805 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5965. Min Act: -0.1700

Data Index: 725869 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5934. Min Act: -0.1700

Data Index: 4331005 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5455. Min Act: -0.1700

Data Index: 110149 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6307. Min Act: -0.1700

Data Index: 5167171 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.6258. Min Act: -0.1700

Data Index: 2707051 (Open Web Text)

Max Activating Token Index: 826

Text #13

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5086. Min Act: -0.1700

Data Index: 7005034 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5835. Min Act: -0.1700

Data Index: 8783637 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5050. Min Act: -0.1700

Data Index: 8050133 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5366. Min Act: -0.1700

Data Index: 4344879 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5371. Min Act: -0.1700

Data Index: 1768685 (Open Web Text)

Max Activating Token Index: 1007

Text #18

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5620. Min Act: -0.1700

Data Index: 1711385 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 5.0167. Min Range: -5.0167

Max Act: 4.5277. Min Act: -0.1700

Data Index: 837703 (Open Web Text)

Max Activating Token Index: 809