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

Dataset: Open Web Text

Neuron 2694 in Layer 6

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: 3.0097. Min Range: -3.0097

Max Act: 3.0097. Min Act: -0.1700

Data Index: 3742662 (Open Web Text)

Max Activating Token Index: 935

Text #1

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9600. Min Act: -0.1700

Data Index: 2514802 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9414. Min Act: -0.1700

Data Index: 434617 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9212. Min Act: -0.1700

Data Index: 3159178 (Open Web Text)

Max Activating Token Index: 674

Text #4

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9251. Min Act: -0.1700

Data Index: 5861866 (Open Web Text)

Max Activating Token Index: 941

Text #5

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8991. Min Act: -0.1700

Data Index: 5075872 (Open Web Text)

Max Activating Token Index: 976

Text #6

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.9042. Min Act: -0.1700

Data Index: 5554424 (Open Web Text)

Max Activating Token Index: 744

Text #7

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8823. Min Act: -0.1700

Data Index: 690715 (Open Web Text)

Max Activating Token Index: 184

Text #8

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8647. Min Act: -0.1700

Data Index: 4672436 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8541. Min Act: -0.1700

Data Index: 8066578 (Open Web Text)

Max Activating Token Index: 205

Text #10

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8404. Min Act: -0.1700

Data Index: 5216623 (Open Web Text)

Max Activating Token Index: 538

Text #11

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8462. Min Act: -0.1700

Data Index: 8012057 (Open Web Text)

Max Activating Token Index: 981

Text #12

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.8102. Min Act: -0.1700

Data Index: 5657811 (Open Web Text)

Max Activating Token Index: 922

Text #13

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7785. Min Act: -0.1700

Data Index: 8758233 (Open Web Text)

Max Activating Token Index: 746

Text #14

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7721. Min Act: -0.1700

Data Index: 5284535 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7642. Min Act: -0.1700

Data Index: 5664736 (Open Web Text)

Max Activating Token Index: 296

Text #16

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7578. Min Act: -0.1700

Data Index: 7695716 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7417. Min Act: -0.1700

Data Index: 3699667 (Open Web Text)

Max Activating Token Index: 928

Text #18

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7659. Min Act: -0.1700

Data Index: 446954 (Open Web Text)

Max Activating Token Index: 512

Text #19

Max Range: 3.0097. Min Range: -3.0097

Max Act: 2.7603. Min Act: -0.1700

Data Index: 2514816 (Open Web Text)

Max Activating Token Index: 256