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

Dataset: Open Web Text

Neuron 210 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: 4.8495. Min Range: -4.8495

Max Act: 4.7976. Min Act: -0.1700

Data Index: 8805166 (Open Web Text)

Max Activating Token Index: 550

Text #1

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.8495. Min Act: -0.1700

Data Index: 346616 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7856. Min Act: -0.1700

Data Index: 5539373 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7976. Min Act: -0.1700

Data Index: 3906134 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7926. Min Act: -0.1700

Data Index: 3716047 (Open Web Text)

Max Activating Token Index: 485

Text #5

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7588. Min Act: -0.1700

Data Index: 6878227 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7393. Min Act: -0.1700

Data Index: 6804581 (Open Web Text)

Max Activating Token Index: 832

Text #7

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7410. Min Act: -0.1700

Data Index: 7975554 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7532. Min Act: -0.1700

Data Index: 3808692 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7484. Min Act: -0.1700

Data Index: 1164852 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7254. Min Act: -0.1700

Data Index: 593541 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7187. Min Act: -0.1700

Data Index: 3778491 (Open Web Text)

Max Activating Token Index: 218

Text #12

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7238. Min Act: -0.1700

Data Index: 4724758 (Open Web Text)

Max Activating Token Index: 362

Text #13

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7568. Min Act: -0.1700

Data Index: 2868212 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.6968. Min Act: -0.1700

Data Index: 8120018 (Open Web Text)

Max Activating Token Index: 858

Text #15

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7288. Min Act: -0.1700

Data Index: 7553934 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7082. Min Act: -0.1700

Data Index: 7607259 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.6967. Min Act: -0.1700

Data Index: 6013419 (Open Web Text)

Max Activating Token Index: 343

Text #18

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.6588. Min Act: -0.1700

Data Index: 5544570 (Open Web Text)

Max Activating Token Index: 787

Text #19

Max Range: 4.8495. Min Range: -4.8495

Max Act: 4.7022. Min Act: -0.1700

Data Index: 517589 (Open Web Text)

Max Activating Token Index: 772