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

Dataset: Open Web Text

Neuron 1363 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: 3.8386. Min Range: -3.8386

Max Act: 3.8375. Min Act: -0.1700

Data Index: 4592943 (Open Web Text)

Max Activating Token Index: 482

Text #1

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7935. Min Act: -0.1700

Data Index: 6329931 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.8386. Min Act: -0.1700

Data Index: 4016930 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.8234. Min Act: -0.1700

Data Index: 6028761 (Open Web Text)

Max Activating Token Index: 976

Text #4

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7945. Min Act: -0.1700

Data Index: 393116 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7636. Min Act: -0.1700

Data Index: 8442545 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7429. Min Act: -0.1700

Data Index: 75474 (Open Web Text)

Max Activating Token Index: 390

Text #7

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7074. Min Act: -0.1700

Data Index: 4696449 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7205. Min Act: -0.1700

Data Index: 963457 (Open Web Text)

Max Activating Token Index: 371

Text #9

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6747. Min Act: -0.1700

Data Index: 5989960 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7143. Min Act: -0.1700

Data Index: 2466115 (Open Web Text)

Max Activating Token Index: 47

Text #11

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7727. Min Act: -0.1700

Data Index: 699133 (Open Web Text)

Max Activating Token Index: 949

Text #12

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6646. Min Act: -0.1700

Data Index: 2447685 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7524. Min Act: -0.1700

Data Index: 5541214 (Open Web Text)

Max Activating Token Index: 979

Text #14

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.7031. Min Act: -0.1700

Data Index: 7233520 (Open Web Text)

Max Activating Token Index: 855

Text #15

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6954. Min Act: -0.1700

Data Index: 2174815 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6639. Min Act: -0.1700

Data Index: 5935403 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6653. Min Act: -0.1700

Data Index: 1553818 (Open Web Text)

Max Activating Token Index: 935

Text #18

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6661. Min Act: -0.1700

Data Index: 1651319 (Open Web Text)

Max Activating Token Index: 858

Text #19

Max Range: 3.8386. Min Range: -3.8386

Max Act: 3.6518. Min Act: -0.1700

Data Index: 475152 (Open Web Text)

Max Activating Token Index: 55