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

Dataset: Open Web Text

Neuron 986 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: 4.1020. Min Range: -4.1020

Max Act: 4.1020. Min Act: -0.1700

Data Index: 4791030 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9855. Min Act: -0.1700

Data Index: 7056301 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9653. Min Act: -0.1700

Data Index: 6699318 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9433. Min Act: -0.1700

Data Index: 4211938 (Open Web Text)

Max Activating Token Index: 508

Text #4

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9485. Min Act: -0.1700

Data Index: 5162444 (Open Web Text)

Max Activating Token Index: 76

Text #5

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9676. Min Act: -0.1700

Data Index: 7960774 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9260. Min Act: -0.1700

Data Index: 2551144 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9390. Min Act: -0.1700

Data Index: 2502388 (Open Web Text)

Max Activating Token Index: 225

Text #8

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8814. Min Act: -0.1700

Data Index: 4781879 (Open Web Text)

Max Activating Token Index: 135

Text #9

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8933. Min Act: -0.1700

Data Index: 8292285 (Open Web Text)

Max Activating Token Index: 976

Text #10

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.9135. Min Act: -0.1700

Data Index: 596958 (Open Web Text)

Max Activating Token Index: 228

Text #11

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8445. Min Act: -0.1700

Data Index: 1964075 (Open Web Text)

Max Activating Token Index: 238

Text #12

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8549. Min Act: -0.1700

Data Index: 6313222 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8732. Min Act: -0.1700

Data Index: 574627 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8517. Min Act: -0.1700

Data Index: 8317016 (Open Web Text)

Max Activating Token Index: 914

Text #15

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8895. Min Act: -0.1700

Data Index: 1395444 (Open Web Text)

Max Activating Token Index: 292

Text #16

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8182. Min Act: -0.1700

Data Index: 5138152 (Open Web Text)

Max Activating Token Index: 131

Text #17

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8268. Min Act: -0.1700

Data Index: 7155092 (Open Web Text)

Max Activating Token Index: 172

Text #18

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8366. Min Act: -0.1700

Data Index: 2443107 (Open Web Text)

Max Activating Token Index: 429

Text #19

Max Range: 4.1020. Min Range: -4.1020

Max Act: 3.8386. Min Act: -0.1700

Data Index: 733190 (Open Web Text)

Max Activating Token Index: 217