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

Dataset: Open Web Text

Neuron 1454 in Layer 5

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: 2.9569. Min Range: -2.9569

Max Act: 2.9569. Min Act: -0.1700

Data Index: 3755163 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.8278. Min Act: -0.1700

Data Index: 2956364 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7824. Min Act: -0.1700

Data Index: 3052786 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.8164. Min Act: -0.1700

Data Index: 3911979 (Open Web Text)

Max Activating Token Index: 684

Text #4

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7672. Min Act: -0.1700

Data Index: 8035927 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7309. Min Act: -0.1700

Data Index: 5661234 (Open Web Text)

Max Activating Token Index: 1003

Text #6

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7559. Min Act: -0.1700

Data Index: 2103696 (Open Web Text)

Max Activating Token Index: 105

Text #7

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7593. Min Act: -0.1700

Data Index: 6828885 (Open Web Text)

Max Activating Token Index: 622

Text #8

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7406. Min Act: -0.1700

Data Index: 7956860 (Open Web Text)

Max Activating Token Index: 856

Text #9

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7310. Min Act: -0.1700

Data Index: 552336 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7243. Min Act: -0.1700

Data Index: 2103695 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6925. Min Act: -0.1700

Data Index: 5341299 (Open Web Text)

Max Activating Token Index: 292

Text #12

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.7180. Min Act: -0.1700

Data Index: 6346455 (Open Web Text)

Max Activating Token Index: 520

Text #13

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6761. Min Act: -0.1700

Data Index: 1653521 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6447. Min Act: -0.1700

Data Index: 2419192 (Open Web Text)

Max Activating Token Index: 563

Text #15

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6490. Min Act: -0.1700

Data Index: 6161160 (Open Web Text)

Max Activating Token Index: 344

Text #16

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6339. Min Act: -0.1700

Data Index: 935787 (Open Web Text)

Max Activating Token Index: 140

Text #17

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6446. Min Act: -0.1700

Data Index: 3214665 (Open Web Text)

Max Activating Token Index: 608

Text #18

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6395. Min Act: -0.1700

Data Index: 2530364 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 2.9569. Min Range: -2.9569

Max Act: 2.6238. Min Act: -0.1700

Data Index: 1110284 (Open Web Text)

Max Activating Token Index: 260