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

Dataset: Open Web Text

Neuron 151 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: 3.2094. Min Range: -3.2094

Max Act: 3.2094. Min Act: -0.1700

Data Index: 7925613 (Open Web Text)

Max Activating Token Index: 194

Text #1

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.1614. Min Act: -0.1700

Data Index: 1872887 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0904. Min Act: -0.1700

Data Index: 4456462 (Open Web Text)

Max Activating Token Index: 701

Text #3

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0275. Min Act: -0.1700

Data Index: 1826084 (Open Web Text)

Max Activating Token Index: 67

Text #4

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0167. Min Act: -0.1700

Data Index: 2033432 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0270. Min Act: -0.1700

Data Index: 1764356 (Open Web Text)

Max Activating Token Index: 78

Text #6

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0024. Min Act: -0.1700

Data Index: 6869172 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0046. Min Act: -0.1700

Data Index: 7441980 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9706. Min Act: -0.1700

Data Index: 3287614 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 3.2094. Min Range: -3.2094

Max Act: 3.0147. Min Act: -0.1700

Data Index: 8069083 (Open Web Text)

Max Activating Token Index: 264

Text #10

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9654. Min Act: -0.1700

Data Index: 1228479 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9831. Min Act: -0.1700

Data Index: 241397 (Open Web Text)

Max Activating Token Index: 301

Text #12

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9439. Min Act: -0.1700

Data Index: 1129960 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9343. Min Act: -0.1700

Data Index: 6638257 (Open Web Text)

Max Activating Token Index: 317

Text #14

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9301. Min Act: -0.1700

Data Index: 4436059 (Open Web Text)

Max Activating Token Index: 39

Text #15

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9189. Min Act: -0.1700

Data Index: 2706432 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9200. Min Act: -0.1700

Data Index: 7925617 (Open Web Text)

Max Activating Token Index: 631

Text #17

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9269. Min Act: -0.1700

Data Index: 2295328 (Open Web Text)

Max Activating Token Index: 625

Text #18

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9250. Min Act: -0.1700

Data Index: 437749 (Open Web Text)

Max Activating Token Index: 838

Text #19

Max Range: 3.2094. Min Range: -3.2094

Max Act: 2.9067. Min Act: -0.1700

Data Index: 6382307 (Open Web Text)

Max Activating Token Index: 85