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

Dataset: Open Web Text

Neuron 783 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: 4.1911. Min Range: -4.1911

Max Act: 4.1911. Min Act: -0.1700

Data Index: 7213861 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.1535. Min Act: -0.1700

Data Index: 5113462 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.1472. Min Act: -0.1700

Data Index: 3011198 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0868. Min Act: -0.1700

Data Index: 4659374 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0952. Min Act: -0.1700

Data Index: 836161 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0920. Min Act: -0.1700

Data Index: 2218186 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0552. Min Act: -0.1700

Data Index: 3084723 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0469. Min Act: -0.1700

Data Index: 7783416 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0501. Min Act: -0.1700

Data Index: 7312976 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0501. Min Act: -0.1700

Data Index: 6315407 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0630. Min Act: -0.1700

Data Index: 5456505 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0483. Min Act: -0.1700

Data Index: 4864104 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0051. Min Act: -0.1700

Data Index: 755036 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0264. Min Act: -0.1700

Data Index: 6923025 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0240. Min Act: -0.1700

Data Index: 2607839 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0109. Min Act: -0.1700

Data Index: 7403634 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0220. Min Act: -0.1700

Data Index: 7516686 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0168. Min Act: -0.1700

Data Index: 3919153 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0177. Min Act: -0.1700

Data Index: 8488583 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.1911. Min Range: -4.1911

Max Act: 4.0020. Min Act: -0.1700

Data Index: 743228 (Open Web Text)

Max Activating Token Index: 4