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

Dataset: Open Web Text

Neuron 2176 in Layer 4

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: 4.0034. Min Range: -4.0034

Max Act: 4.0034. Min Act: -0.1700

Data Index: 4161725 (Open Web Text)

Max Activating Token Index: 1000

Text #1

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.8968. Min Act: -0.1700

Data Index: 1982019 (Open Web Text)

Max Activating Token Index: 562

Text #2

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7878. Min Act: -0.1700

Data Index: 5756246 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7884. Min Act: -0.1700

Data Index: 992324 (Open Web Text)

Max Activating Token Index: 463

Text #4

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.8238. Min Act: -0.1700

Data Index: 4660787 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7561. Min Act: -0.1700

Data Index: 5365512 (Open Web Text)

Max Activating Token Index: 451

Text #6

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7652. Min Act: -0.1700

Data Index: 826626 (Open Web Text)

Max Activating Token Index: 217

Text #7

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7719. Min Act: -0.1700

Data Index: 2421809 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7752. Min Act: -0.1700

Data Index: 8319974 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7694. Min Act: -0.1700

Data Index: 2377132 (Open Web Text)

Max Activating Token Index: 651

Text #10

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7413. Min Act: -0.1700

Data Index: 1796099 (Open Web Text)

Max Activating Token Index: 433

Text #11

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.7341. Min Act: -0.1700

Data Index: 3506140 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6982. Min Act: -0.1700

Data Index: 4201686 (Open Web Text)

Max Activating Token Index: 393

Text #13

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6747. Min Act: -0.1700

Data Index: 7312963 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6607. Min Act: -0.1700

Data Index: 8230642 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6654. Min Act: -0.1700

Data Index: 7206653 (Open Web Text)

Max Activating Token Index: 274

Text #16

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6435. Min Act: -0.1700

Data Index: 7608669 (Open Web Text)

Max Activating Token Index: 834

Text #17

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6808. Min Act: -0.1700

Data Index: 598769 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6386. Min Act: -0.1700

Data Index: 5792450 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 4.0034. Min Range: -4.0034

Max Act: 3.6771. Min Act: -0.1700

Data Index: 6262022 (Open Web Text)

Max Activating Token Index: 510