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

Dataset: Open Web Text

Neuron 1220 in Layer 6

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: 4.3906. Min Range: -4.3906

Max Act: 4.3906. Min Act: -0.1700

Data Index: 5280108 (Open Web Text)

Max Activating Token Index: 295

Text #1

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.2345. Min Act: -0.1700

Data Index: 8299977 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1835. Min Act: -0.1700

Data Index: 2790313 (Open Web Text)

Max Activating Token Index: 377

Text #3

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1587. Min Act: -0.1700

Data Index: 2387171 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1762. Min Act: -0.1700

Data Index: 417667 (Open Web Text)

Max Activating Token Index: 41

Text #5

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0981. Min Act: -0.1700

Data Index: 4201588 (Open Web Text)

Max Activating Token Index: 593

Text #6

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1317. Min Act: -0.1700

Data Index: 943698 (Open Web Text)

Max Activating Token Index: 718

Text #7

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1272. Min Act: -0.1700

Data Index: 8642082 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1384. Min Act: -0.1700

Data Index: 2176385 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0937. Min Act: -0.1700

Data Index: 3961331 (Open Web Text)

Max Activating Token Index: 757

Text #10

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1250. Min Act: -0.1700

Data Index: 4994039 (Open Web Text)

Max Activating Token Index: 412

Text #11

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1143. Min Act: -0.1700

Data Index: 1563643 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1081. Min Act: -0.1700

Data Index: 1597328 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.1002. Min Act: -0.1700

Data Index: 4469040 (Open Web Text)

Max Activating Token Index: 51

Text #14

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0846. Min Act: -0.1700

Data Index: 8317930 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0490. Min Act: -0.1700

Data Index: 6470803 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0736. Min Act: -0.1700

Data Index: 1515879 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0538. Min Act: -0.1700

Data Index: 2253091 (Open Web Text)

Max Activating Token Index: 887

Text #18

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0670. Min Act: -0.1700

Data Index: 6926963 (Open Web Text)

Max Activating Token Index: 686

Text #19

Max Range: 4.3906. Min Range: -4.3906

Max Act: 4.0629. Min Act: -0.1700

Data Index: 816825 (Open Web Text)

Max Activating Token Index: 773