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

Dataset: Open Web Text

Neuron 1635 in Layer 3

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: 4.4751. Min Range: -4.4751

Max Act: 4.4751. Min Act: -0.1700

Data Index: 572435 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.4734. Min Act: -0.1700

Data Index: 953100 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3980. Min Act: -0.1700

Data Index: 6142698 (Open Web Text)

Max Activating Token Index: 203

Text #3

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3976. Min Act: -0.1700

Data Index: 7782992 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3780. Min Act: -0.1700

Data Index: 1429859 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3583. Min Act: -0.1700

Data Index: 2468442 (Open Web Text)

Max Activating Token Index: 511

Text #6

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3515. Min Act: -0.1700

Data Index: 4301296 (Open Web Text)

Max Activating Token Index: 821

Text #7

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2961. Min Act: -0.1700

Data Index: 5805688 (Open Web Text)

Max Activating Token Index: 827

Text #8

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3493. Min Act: -0.1700

Data Index: 2002240 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3278. Min Act: -0.1700

Data Index: 7130821 (Open Web Text)

Max Activating Token Index: 218

Text #10

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2979. Min Act: -0.1700

Data Index: 2068198 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2727. Min Act: -0.1700

Data Index: 3402999 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2657. Min Act: -0.1700

Data Index: 7490049 (Open Web Text)

Max Activating Token Index: 571

Text #13

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2734. Min Act: -0.1700

Data Index: 2372359 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3118. Min Act: -0.1700

Data Index: 5805689 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2968. Min Act: -0.1700

Data Index: 1723475 (Open Web Text)

Max Activating Token Index: 360

Text #16

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2842. Min Act: -0.1700

Data Index: 5993788 (Open Web Text)

Max Activating Token Index: 488

Text #17

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.3016. Min Act: -0.1700

Data Index: 1406946 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2681. Min Act: -0.1700

Data Index: 1135353 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 4.4751. Min Range: -4.4751

Max Act: 4.2733. Min Act: -0.1700

Data Index: 3908541 (Open Web Text)

Max Activating Token Index: 687