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

Dataset: Open Web Text

Neuron 85 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: 2.0993. Min Range: -2.0993

Max Act: 2.0993. Min Act: -0.1700

Data Index: 7273839 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0793. Min Act: -0.1700

Data Index: 6607461 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0839. Min Act: -0.1700

Data Index: 3274831 (Open Web Text)

Max Activating Token Index: 781

Text #3

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0493. Min Act: -0.1700

Data Index: 8138904 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0553. Min Act: -0.1700

Data Index: 5968736 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0281. Min Act: -0.1700

Data Index: 6657655 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0361. Min Act: -0.1700

Data Index: 4720932 (Open Web Text)

Max Activating Token Index: 474

Text #7

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0244. Min Act: -0.1700

Data Index: 8776811 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0335. Min Act: -0.1700

Data Index: 8745876 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0084. Min Act: -0.1700

Data Index: 8745898 (Open Web Text)

Max Activating Token Index: 1001

Text #10

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0191. Min Act: -0.1700

Data Index: 3207108 (Open Web Text)

Max Activating Token Index: 839

Text #11

Max Range: 2.0993. Min Range: -2.0993

Max Act: 2.0019. Min Act: -0.1700

Data Index: 3155754 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9998. Min Act: -0.1700

Data Index: 6933525 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9970. Min Act: -0.1700

Data Index: 6597889 (Open Web Text)

Max Activating Token Index: 788

Text #14

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9711. Min Act: -0.1700

Data Index: 3736136 (Open Web Text)

Max Activating Token Index: 856

Text #15

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9876. Min Act: -0.1700

Data Index: 5915359 (Open Web Text)

Max Activating Token Index: 850

Text #16

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9795. Min Act: -0.1700

Data Index: 4154339 (Open Web Text)

Max Activating Token Index: 373

Text #17

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9728. Min Act: -0.1700

Data Index: 2207986 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9830. Min Act: -0.1700

Data Index: 6008386 (Open Web Text)

Max Activating Token Index: 784

Text #19

Max Range: 2.0993. Min Range: -2.0993

Max Act: 1.9804. Min Act: -0.1700

Data Index: 6484734 (Open Web Text)

Max Activating Token Index: 905