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

Dataset: Open Web Text

Neuron 870 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: 4.3127. Min Range: -4.3127

Max Act: 4.3127. Min Act: -0.1700

Data Index: 5008166 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.2858. Min Act: -0.1700

Data Index: 3704969 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.1993. Min Act: -0.1700

Data Index: 7357269 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.1724. Min Act: -0.1700

Data Index: 8310425 (Open Web Text)

Max Activating Token Index: 605

Text #4

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.1271. Min Act: -0.1700

Data Index: 6783905 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0757. Min Act: -0.1700

Data Index: 5228330 (Open Web Text)

Max Activating Token Index: 98

Text #6

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0999. Min Act: -0.1700

Data Index: 5508139 (Open Web Text)

Max Activating Token Index: 369

Text #7

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0955. Min Act: -0.1700

Data Index: 2513469 (Open Web Text)

Max Activating Token Index: 969

Text #8

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0281. Min Act: -0.1700

Data Index: 4441835 (Open Web Text)

Max Activating Token Index: 92

Text #9

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0180. Min Act: -0.1700

Data Index: 5678813 (Open Web Text)

Max Activating Token Index: 951

Text #10

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0883. Min Act: -0.1700

Data Index: 5652039 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0135. Min Act: -0.1700

Data Index: 4211162 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0200. Min Act: -0.1700

Data Index: 8805088 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0152. Min Act: -0.1700

Data Index: 4004451 (Open Web Text)

Max Activating Token Index: 937

Text #14

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0165. Min Act: -0.1700

Data Index: 8024010 (Open Web Text)

Max Activating Token Index: 422

Text #15

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0414. Min Act: -0.1700

Data Index: 4742460 (Open Web Text)

Max Activating Token Index: 792

Text #16

Max Range: 4.3127. Min Range: -4.3127

Max Act: 4.0317. Min Act: -0.1700

Data Index: 900865 (Open Web Text)

Max Activating Token Index: 535

Text #17

Max Range: 4.3127. Min Range: -4.3127

Max Act: 3.9726. Min Act: -0.1700

Data Index: 2378538 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 4.3127. Min Range: -4.3127

Max Act: 3.9799. Min Act: -0.1700

Data Index: 2523432 (Open Web Text)

Max Activating Token Index: 51

Text #19

Max Range: 4.3127. Min Range: -4.3127

Max Act: 3.9947. Min Act: -0.1700

Data Index: 7711688 (Open Web Text)

Max Activating Token Index: 673