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

Dataset: Open Web Text

Neuron 1063 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: 2.4145. Min Range: -2.4145

Max Act: 2.4145. Min Act: -0.1700

Data Index: 3830885 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2959. Min Act: -0.1700

Data Index: 4051138 (Open Web Text)

Max Activating Token Index: 788

Text #2

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2941. Min Act: -0.1700

Data Index: 8745362 (Open Web Text)

Max Activating Token Index: 354

Text #3

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2440. Min Act: -0.1700

Data Index: 1448196 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2440. Min Act: -0.1700

Data Index: 4814690 (Open Web Text)

Max Activating Token Index: 514

Text #5

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2577. Min Act: -0.1700

Data Index: 3329378 (Open Web Text)

Max Activating Token Index: 584

Text #6

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2677. Min Act: -0.1700

Data Index: 8070686 (Open Web Text)

Max Activating Token Index: 619

Text #7

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2247. Min Act: -0.1700

Data Index: 8555871 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2114. Min Act: -0.1700

Data Index: 6659704 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1889. Min Act: -0.1700

Data Index: 6760880 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2044. Min Act: -0.1700

Data Index: 1435470 (Open Web Text)

Max Activating Token Index: 526

Text #11

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.2042. Min Act: -0.1700

Data Index: 4101848 (Open Web Text)

Max Activating Token Index: 324

Text #12

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1959. Min Act: -0.1700

Data Index: 8671814 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1936. Min Act: -0.1700

Data Index: 6615594 (Open Web Text)

Max Activating Token Index: 482

Text #14

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1935. Min Act: -0.1700

Data Index: 219417 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1777. Min Act: -0.1700

Data Index: 3449809 (Open Web Text)

Max Activating Token Index: 140

Text #16

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1631. Min Act: -0.1700

Data Index: 8070685 (Open Web Text)

Max Activating Token Index: 766

Text #17

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1949. Min Act: -0.1700

Data Index: 7078786 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1559. Min Act: -0.1700

Data Index: 125454 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.4145. Min Range: -2.4145

Max Act: 2.1559. Min Act: -0.1700

Data Index: 5442908 (Open Web Text)

Max Activating Token Index: 2