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

Dataset: Open Web Text

Neuron 897 in Layer 3

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: 4.4746. Min Range: -4.4746

Max Act: 4.4746. Min Act: -0.1700

Data Index: 1359217 (Open Web Text)

Max Activating Token Index: 429

Text #1

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.3504. Min Act: -0.1700

Data Index: 989994 (Open Web Text)

Max Activating Token Index: 127

Text #2

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.3025. Min Act: -0.1700

Data Index: 2433665 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.2634. Min Act: -0.1700

Data Index: 1359215 (Open Web Text)

Max Activating Token Index: 176

Text #4

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.2800. Min Act: -0.1700

Data Index: 2022040 (Open Web Text)

Max Activating Token Index: 58

Text #5

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.2132. Min Act: -0.1700

Data Index: 989995 (Open Web Text)

Max Activating Token Index: 325

Text #6

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1676. Min Act: -0.1700

Data Index: 3935670 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1800. Min Act: -0.1700

Data Index: 3935669 (Open Web Text)

Max Activating Token Index: 518

Text #8

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1879. Min Act: -0.1700

Data Index: 989992 (Open Web Text)

Max Activating Token Index: 89

Text #9

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1255. Min Act: -0.1700

Data Index: 989981 (Open Web Text)

Max Activating Token Index: 995

Text #10

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1711. Min Act: -0.1700

Data Index: 5178181 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1254. Min Act: -0.1700

Data Index: 1397371 (Open Web Text)

Max Activating Token Index: 817

Text #12

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.0883. Min Act: -0.1700

Data Index: 7745339 (Open Web Text)

Max Activating Token Index: 666

Text #13

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1282. Min Act: -0.1700

Data Index: 3935673 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1152. Min Act: -0.1700

Data Index: 299107 (Open Web Text)

Max Activating Token Index: 428

Text #15

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.0891. Min Act: -0.1700

Data Index: 6273056 (Open Web Text)

Max Activating Token Index: 87

Text #16

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.0959. Min Act: -0.1700

Data Index: 3068157 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.0971. Min Act: -0.1700

Data Index: 3288056 (Open Web Text)

Max Activating Token Index: 538

Text #18

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.1237. Min Act: -0.1700

Data Index: 1359214 (Open Web Text)

Max Activating Token Index: 1008

Text #19

Max Range: 4.4746. Min Range: -4.4746

Max Act: 4.0735. Min Act: -0.1700

Data Index: 3935676 (Open Web Text)

Max Activating Token Index: 229