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

Dataset: Open Web Text

Neuron 819 in Layer 0

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: 3.2453. Min Range: -3.2453

Max Act: 3.2453. Min Act: -0.1700

Data Index: 7772008 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1477. Min Act: -0.1700

Data Index: 628079 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1455. Min Act: -0.1700

Data Index: 4583985 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1451. Min Act: -0.1700

Data Index: 666369 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1484. Min Act: -0.1700

Data Index: 3612280 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1379. Min Act: -0.1700

Data Index: 5085497 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1408. Min Act: -0.1700

Data Index: 7160720 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1255. Min Act: -0.1700

Data Index: 7440550 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1146. Min Act: -0.1700

Data Index: 7837010 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1287. Min Act: -0.1700

Data Index: 2542163 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1050. Min Act: -0.1700

Data Index: 5323009 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1043. Min Act: -0.1700

Data Index: 3258793 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.1043. Min Act: -0.1700

Data Index: 671118 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0973. Min Act: -0.1700

Data Index: 5686252 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0998. Min Act: -0.1700

Data Index: 3739630 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0891. Min Act: -0.1700

Data Index: 3645790 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0991. Min Act: -0.1700

Data Index: 3292896 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0711. Min Act: -0.1700

Data Index: 4794123 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0819. Min Act: -0.1700

Data Index: 6258219 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.2453. Min Range: -3.2453

Max Act: 3.0767. Min Act: -0.1700

Data Index: 1007879 (Open Web Text)

Max Activating Token Index: 11