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

Dataset: Open Web Text

Neuron 2865 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: 1.8121. Min Range: -1.8121

Max Act: 1.8121. Min Act: -0.1700

Data Index: 1816440 (Open Web Text)

Max Activating Token Index: 699

Text #1

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7727. Min Act: -0.1700

Data Index: 737409 (Open Web Text)

Max Activating Token Index: 741

Text #2

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7365. Min Act: -0.1700

Data Index: 8729806 (Open Web Text)

Max Activating Token Index: 717

Text #3

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7219. Min Act: -0.1700

Data Index: 1341002 (Open Web Text)

Max Activating Token Index: 368

Text #4

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7052. Min Act: -0.1700

Data Index: 3623656 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.7024. Min Act: -0.1700

Data Index: 2611883 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6898. Min Act: -0.1700

Data Index: 2905988 (Open Web Text)

Max Activating Token Index: 131

Text #7

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6981. Min Act: -0.1700

Data Index: 8313936 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6904. Min Act: -0.1700

Data Index: 482331 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6865. Min Act: -0.1700

Data Index: 4204424 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6878. Min Act: -0.1700

Data Index: 773074 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6799. Min Act: -0.1700

Data Index: 4563532 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6847. Min Act: -0.1700

Data Index: 5634668 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6728. Min Act: -0.1700

Data Index: 6503335 (Open Web Text)

Max Activating Token Index: 522

Text #14

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6788. Min Act: -0.1700

Data Index: 2615141 (Open Web Text)

Max Activating Token Index: 430

Text #15

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6683. Min Act: -0.1700

Data Index: 6573417 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6725. Min Act: -0.1700

Data Index: 7017688 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6753. Min Act: -0.1700

Data Index: 3187043 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6684. Min Act: -0.1700

Data Index: 1432831 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 1.8121. Min Range: -1.8121

Max Act: 1.6807. Min Act: -0.1700

Data Index: 7189100 (Open Web Text)

Max Activating Token Index: 825