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

Dataset: Open Web Text

Neuron 1928 in Layer 1

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: 3.6727. Min Range: -3.6727

Max Act: 3.6630. Min Act: -0.1700

Data Index: 2857192 (Open Web Text)

Max Activating Token Index: 409

Text #1

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6727. Min Act: -0.1700

Data Index: 5673419 (Open Web Text)

Max Activating Token Index: 658

Text #2

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1973165 (Open Web Text)

Max Activating Token Index: 888

Text #3

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6437. Min Act: -0.1700

Data Index: 4467484 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6324. Min Act: -0.1700

Data Index: 865191 (Open Web Text)

Max Activating Token Index: 1000

Text #5

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6294. Min Act: -0.1700

Data Index: 2207177 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6316. Min Act: -0.1700

Data Index: 6033158 (Open Web Text)

Max Activating Token Index: 271

Text #7

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6187. Min Act: -0.1700

Data Index: 670057 (Open Web Text)

Max Activating Token Index: 739

Text #8

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6111. Min Act: -0.1700

Data Index: 3289441 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6089. Min Act: -0.1700

Data Index: 3275844 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.6091. Min Act: -0.1700

Data Index: 5240026 (Open Web Text)

Max Activating Token Index: 236

Text #11

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5825. Min Act: -0.1700

Data Index: 521910 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5927. Min Act: -0.1700

Data Index: 522813 (Open Web Text)

Max Activating Token Index: 102

Text #13

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5925. Min Act: -0.1700

Data Index: 6445392 (Open Web Text)

Max Activating Token Index: 478

Text #14

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5858. Min Act: -0.1700

Data Index: 4207124 (Open Web Text)

Max Activating Token Index: 247

Text #15

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5800. Min Act: -0.1700

Data Index: 5182081 (Open Web Text)

Max Activating Token Index: 128

Text #16

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5598. Min Act: -0.1700

Data Index: 3038471 (Open Web Text)

Max Activating Token Index: 982

Text #17

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5796. Min Act: -0.1700

Data Index: 4789531 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1594838 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 3.6727. Min Range: -3.6727

Max Act: 3.5791. Min Act: -0.1700

Data Index: 4348912 (Open Web Text)

Max Activating Token Index: 361