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

Dataset: Open Web Text

Neuron 1550 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: 3.3663. Min Range: -3.3663

Max Act: 3.3663. Min Act: -0.1700

Data Index: 2411740 (Open Web Text)

Max Activating Token Index: 754

Text #1

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.3017. Min Act: -0.1700

Data Index: 3051775 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.3239. Min Act: -0.1700

Data Index: 6851228 (Open Web Text)

Max Activating Token Index: 98

Text #3

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2841. Min Act: -0.1700

Data Index: 4188264 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2633. Min Act: -0.1700

Data Index: 6960312 (Open Web Text)

Max Activating Token Index: 786

Text #5

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2562. Min Act: -0.1700

Data Index: 3721283 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2537. Min Act: -0.1700

Data Index: 5528643 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2441. Min Act: -0.1700

Data Index: 5854252 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2420. Min Act: -0.1700

Data Index: 655680 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2487. Min Act: -0.1700

Data Index: 4804757 (Open Web Text)

Max Activating Token Index: 63

Text #10

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2341. Min Act: -0.1700

Data Index: 3543841 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2406. Min Act: -0.1700

Data Index: 1976554 (Open Web Text)

Max Activating Token Index: 57

Text #12

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2013. Min Act: -0.1700

Data Index: 1415346 (Open Web Text)

Max Activating Token Index: 283

Text #13

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.1930. Min Act: -0.1700

Data Index: 1272158 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2068. Min Act: -0.1700

Data Index: 7357897 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1738906 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.2064. Min Act: -0.1700

Data Index: 5808257 (Open Web Text)

Max Activating Token Index: 28

Text #17

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.1892. Min Act: -0.1700

Data Index: 6783423 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.1788. Min Act: -0.1700

Data Index: 6520552 (Open Web Text)

Max Activating Token Index: 113

Text #19

Max Range: 3.3663. Min Range: -3.3663

Max Act: 3.1705. Min Act: -0.1700

Data Index: 4917962 (Open Web Text)

Max Activating Token Index: 128