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

Dataset: Open Web Text

Neuron 2436 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: 2.6139. Min Range: -2.6139

Max Act: 2.6139. Min Act: -0.1700

Data Index: 8223023 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.5834. Min Act: -0.1700

Data Index: 8686672 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.5412. Min Act: -0.1700

Data Index: 5387280 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.5404. Min Act: -0.1700

Data Index: 5441112 (Open Web Text)

Max Activating Token Index: 32

Text #4

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.5224. Min Act: -0.1700

Data Index: 3732888 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.5201. Min Act: -0.1700

Data Index: 4459118 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4932. Min Act: -0.1700

Data Index: 654963 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4995. Min Act: -0.1700

Data Index: 7552467 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4901. Min Act: -0.1700

Data Index: 5980933 (Open Web Text)

Max Activating Token Index: 362

Text #9

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4848. Min Act: -0.1700

Data Index: 708006 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4814. Min Act: -0.1700

Data Index: 8811438 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4544. Min Act: -0.1700

Data Index: 3056129 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4409. Min Act: -0.1691

Data Index: 654964 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4357. Min Act: -0.1700

Data Index: 3216149 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4268. Min Act: -0.1700

Data Index: 7353402 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4296. Min Act: -0.1700

Data Index: 7267842 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4254. Min Act: -0.1700

Data Index: 654966 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4260. Min Act: -0.1700

Data Index: 3857447 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4316. Min Act: -0.1698

Data Index: 654965 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 2.6139. Min Range: -2.6139

Max Act: 2.4157. Min Act: -0.1700

Data Index: 6108795 (Open Web Text)

Max Activating Token Index: 10