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

Dataset: Open Web Text

Neuron 770 in Layer 4

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: 4.4089. Min Range: -4.4089

Max Act: 4.3914. Min Act: -0.1700

Data Index: 7605375 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.4089. Min Act: -0.1700

Data Index: 5883365 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.3982. Min Act: -0.1700

Data Index: 4786949 (Open Web Text)

Max Activating Token Index: 303

Text #3

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.3445. Min Act: -0.1700

Data Index: 6452803 (Open Web Text)

Max Activating Token Index: 672

Text #4

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2941. Min Act: -0.1700

Data Index: 4055194 (Open Web Text)

Max Activating Token Index: 646

Text #5

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2645. Min Act: -0.1700

Data Index: 3348582 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2718. Min Act: -0.1700

Data Index: 1440046 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2770. Min Act: -0.1700

Data Index: 2786388 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2955. Min Act: -0.1700

Data Index: 6430616 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.3045. Min Act: -0.1700

Data Index: 3971432 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2495. Min Act: -0.1700

Data Index: 3237695 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2286. Min Act: -0.1700

Data Index: 7501067 (Open Web Text)

Max Activating Token Index: 889

Text #12

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2410. Min Act: -0.1700

Data Index: 1286358 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2792. Min Act: -0.1700

Data Index: 4569800 (Open Web Text)

Max Activating Token Index: 885

Text #14

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2330. Min Act: -0.1700

Data Index: 5281876 (Open Web Text)

Max Activating Token Index: 704

Text #15

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2410. Min Act: -0.1700

Data Index: 5021994 (Open Web Text)

Max Activating Token Index: 122

Text #16

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2547. Min Act: -0.1700

Data Index: 6783335 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2543. Min Act: -0.1700

Data Index: 7000218 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2241. Min Act: -0.1700

Data Index: 804340 (Open Web Text)

Max Activating Token Index: 564

Text #19

Max Range: 4.4089. Min Range: -4.4089

Max Act: 4.2305. Min Act: -0.1700

Data Index: 6382814 (Open Web Text)

Max Activating Token Index: 181