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

Dataset: Open Web Text

Neuron 1221 in Layer 2

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: 1.7240. Min Range: -1.7240

Max Act: 1.7240. Min Act: -0.1700

Data Index: 1796621 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6891. Min Act: -0.1679

Data Index: 6658480 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6867. Min Act: -0.1699

Data Index: 3757008 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6455. Min Act: -0.1700

Data Index: 871053 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6296. Min Act: -0.1700

Data Index: 631779 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6228. Min Act: -0.1700

Data Index: 5461225 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6464. Min Act: -0.1699

Data Index: 5053143 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6148. Min Act: -0.1700

Data Index: 7901612 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6145. Min Act: -0.1700

Data Index: 6408613 (Open Web Text)

Max Activating Token Index: 941

Text #9

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6318. Min Act: -0.1678

Data Index: 717039 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6036. Min Act: -0.1700

Data Index: 3031569 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6169. Min Act: -0.1700

Data Index: 5990366 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.6175. Min Act: -0.1697

Data Index: 2482601 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5972. Min Act: -0.1700

Data Index: 3549244 (Open Web Text)

Max Activating Token Index: 832

Text #14

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5980. Min Act: -0.1700

Data Index: 3144768 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5798. Min Act: -0.1699

Data Index: 3934733 (Open Web Text)

Max Activating Token Index: 1005

Text #16

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5939. Min Act: -0.1699

Data Index: 1082075 (Open Web Text)

Max Activating Token Index: 489

Text #17

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5932. Min Act: -0.1699

Data Index: 2033376 (Open Web Text)

Max Activating Token Index: 67

Text #18

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5780. Min Act: -0.1697

Data Index: 4000118 (Open Web Text)

Max Activating Token Index: 487

Text #19

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.5822. Min Act: -0.1699

Data Index: 2063095 (Open Web Text)

Max Activating Token Index: 256