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

Dataset: Open Web Text

Neuron 1375 in Layer 2

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: 4.0849. Min Range: -4.0849

Max Act: 4.0849. Min Act: -0.1700

Data Index: 535638 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 4.0849. Min Range: -4.0849

Max Act: 4.0141. Min Act: -0.1700

Data Index: 5379673 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 4.0849. Min Range: -4.0849

Max Act: 4.0317. Min Act: -0.1700

Data Index: 2070794 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 4.0849. Min Range: -4.0849

Max Act: 4.0146. Min Act: -0.1700

Data Index: 2303527 (Open Web Text)

Max Activating Token Index: 711

Text #4

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.9560. Min Act: -0.1700

Data Index: 3447234 (Open Web Text)

Max Activating Token Index: 357

Text #5

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.9242. Min Act: -0.1700

Data Index: 5755722 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8948. Min Act: -0.1700

Data Index: 5964169 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.9091. Min Act: -0.1700

Data Index: 460752 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8947. Min Act: -0.1700

Data Index: 6578783 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8941. Min Act: -0.1700

Data Index: 8000362 (Open Web Text)

Max Activating Token Index: 914

Text #10

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.9159. Min Act: -0.1700

Data Index: 7870623 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8533. Min Act: -0.1700

Data Index: 8131186 (Open Web Text)

Max Activating Token Index: 159

Text #12

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8836. Min Act: -0.1700

Data Index: 1210565 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8894. Min Act: -0.1700

Data Index: 8125695 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8897. Min Act: -0.1700

Data Index: 229107 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8548. Min Act: -0.1700

Data Index: 8341055 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8411. Min Act: -0.1700

Data Index: 1771047 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8052. Min Act: -0.1700

Data Index: 4691750 (Open Web Text)

Max Activating Token Index: 253

Text #18

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8265. Min Act: -0.1700

Data Index: 7960212 (Open Web Text)

Max Activating Token Index: 500

Text #19

Max Range: 4.0849. Min Range: -4.0849

Max Act: 3.8453. Min Act: -0.1700

Data Index: 4100030 (Open Web Text)

Max Activating Token Index: 374