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

Dataset: Open Web Text

Neuron 1867 in Layer 1

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: 2.2174. Min Range: -2.2174

Max Act: 2.2159. Min Act: -0.1700

Data Index: 5424244 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.2122. Min Act: -0.1700

Data Index: 2791753 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.2174. Min Act: -0.1700

Data Index: 7188753 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1841. Min Act: -0.1700

Data Index: 2608283 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1963. Min Act: -0.1700

Data Index: 760069 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1935. Min Act: -0.1700

Data Index: 8380560 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1811. Min Act: -0.1700

Data Index: 1252953 (Open Web Text)

Max Activating Token Index: 46

Text #7

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1813. Min Act: -0.1700

Data Index: 291876 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1767. Min Act: -0.1700

Data Index: 4320689 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1716. Min Act: -0.1700

Data Index: 4320675 (Open Web Text)

Max Activating Token Index: 351

Text #10

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1737. Min Act: -0.1700

Data Index: 8771597 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1863. Min Act: -0.1700

Data Index: 2318130 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1697. Min Act: -0.1700

Data Index: 6022736 (Open Web Text)

Max Activating Token Index: 538

Text #13

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1767. Min Act: -0.1700

Data Index: 2871105 (Open Web Text)

Max Activating Token Index: 66

Text #14

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1505. Min Act: -0.1700

Data Index: 336798 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1761. Min Act: -0.1700

Data Index: 845015 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1566. Min Act: -0.1700

Data Index: 5476320 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1500. Min Act: -0.1700

Data Index: 581611 (Open Web Text)

Max Activating Token Index: 63

Text #18

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1487. Min Act: -0.1700

Data Index: 4458235 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 2.2174. Min Range: -2.2174

Max Act: 2.1411. Min Act: -0.1700

Data Index: 4737544 (Open Web Text)

Max Activating Token Index: 26