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

Dataset: Open Web Text

Neuron 792 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: 1.9976. Min Range: -1.9976

Max Act: 1.9976. Min Act: -0.1700

Data Index: 8215631 (Open Web Text)

Max Activating Token Index: 104

Text #1

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.9648. Min Act: -0.1700

Data Index: 3189404 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.9110. Min Act: -0.1700

Data Index: 2884207 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.9014. Min Act: -0.1700

Data Index: 6820688 (Open Web Text)

Max Activating Token Index: 623

Text #4

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8971. Min Act: -0.1700

Data Index: 3646324 (Open Web Text)

Max Activating Token Index: 883

Text #5

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8847. Min Act: -0.1700

Data Index: 3279467 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8797. Min Act: -0.1700

Data Index: 8339208 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8744. Min Act: -0.1700

Data Index: 1411674 (Open Web Text)

Max Activating Token Index: 214

Text #8

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8711. Min Act: -0.1700

Data Index: 5522778 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8725. Min Act: -0.1700

Data Index: 6598118 (Open Web Text)

Max Activating Token Index: 32

Text #10

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8864. Min Act: -0.1700

Data Index: 1767507 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8648. Min Act: -0.1700

Data Index: 1763248 (Open Web Text)

Max Activating Token Index: 287

Text #12

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8650. Min Act: -0.1700

Data Index: 7734556 (Open Web Text)

Max Activating Token Index: 380

Text #13

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8653. Min Act: -0.1700

Data Index: 5645970 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8726. Min Act: -0.1700

Data Index: 6011849 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8729. Min Act: -0.1700

Data Index: 5087036 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8615. Min Act: -0.1700

Data Index: 3892558 (Open Web Text)

Max Activating Token Index: 111

Text #17

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8424. Min Act: -0.1700

Data Index: 5532992 (Open Web Text)

Max Activating Token Index: 697

Text #18

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8580. Min Act: -0.1700

Data Index: 1462650 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 1.9976. Min Range: -1.9976

Max Act: 1.8295. Min Act: -0.1700

Data Index: 4113194 (Open Web Text)

Max Activating Token Index: 369