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

Dataset: Open Web Text

Neuron 1520 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: 1.5822. Min Range: -1.5822

Max Act: 1.5822. Min Act: -0.1700

Data Index: 7449322 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.5104. Min Act: -0.1700

Data Index: 7065599 (Open Web Text)

Max Activating Token Index: 851

Text #2

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.5092. Min Act: -0.1700

Data Index: 4071958 (Open Web Text)

Max Activating Token Index: 476

Text #3

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.5124. Min Act: -0.1700

Data Index: 8216787 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4916. Min Act: -0.1698

Data Index: 3905600 (Open Web Text)

Max Activating Token Index: 224

Text #5

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4865. Min Act: -0.1700

Data Index: 3820797 (Open Web Text)

Max Activating Token Index: 842

Text #6

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4813. Min Act: -0.1700

Data Index: 1086455 (Open Web Text)

Max Activating Token Index: 538

Text #7

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4664. Min Act: -0.1700

Data Index: 5650063 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4762. Min Act: -0.1700

Data Index: 5071983 (Open Web Text)

Max Activating Token Index: 845

Text #9

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4682. Min Act: -0.1700

Data Index: 6592769 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4722. Min Act: -0.1700

Data Index: 3500281 (Open Web Text)

Max Activating Token Index: 292

Text #11

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4644. Min Act: -0.1700

Data Index: 4422382 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4594. Min Act: -0.1700

Data Index: 102902 (Open Web Text)

Max Activating Token Index: 609

Text #13

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4585. Min Act: -0.1700

Data Index: 4765127 (Open Web Text)

Max Activating Token Index: 389

Text #14

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4641. Min Act: -0.1700

Data Index: 36630 (Open Web Text)

Max Activating Token Index: 438

Text #15

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4545. Min Act: -0.1700

Data Index: 473970 (Open Web Text)

Max Activating Token Index: 999

Text #16

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4584. Min Act: -0.1700

Data Index: 6249375 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4467. Min Act: -0.1700

Data Index: 4814617 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4501. Min Act: -0.1700

Data Index: 7047946 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4514. Min Act: -0.1700

Data Index: 6436546 (Open Web Text)

Max Activating Token Index: 541