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

Dataset: Open Web Text

Neuron 1328 in Layer 4

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: 6.1336. Min Range: -6.1336

Max Act: 6.1336. Min Act: -0.1700

Data Index: 6055755 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.9258. Min Act: -0.1700

Data Index: 7113923 (Open Web Text)

Max Activating Token Index: 230

Text #2

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8904. Min Act: -0.1700

Data Index: 5626966 (Open Web Text)

Max Activating Token Index: 207

Text #3

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8974. Min Act: -0.1700

Data Index: 1073275 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.7989. Min Act: -0.1700

Data Index: 6958820 (Open Web Text)

Max Activating Token Index: 135

Text #5

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8129. Min Act: -0.1700

Data Index: 1578936 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8046. Min Act: -0.1700

Data Index: 749993 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.7457. Min Act: -0.1700

Data Index: 1501359 (Open Web Text)

Max Activating Token Index: 928

Text #8

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8077. Min Act: -0.1700

Data Index: 6617050 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.7650. Min Act: -0.1700

Data Index: 668653 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.7320. Min Act: -0.1700

Data Index: 7983870 (Open Web Text)

Max Activating Token Index: 78

Text #11

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.8034. Min Act: -0.1700

Data Index: 4270116 (Open Web Text)

Max Activating Token Index: 422

Text #12

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.7023. Min Act: -0.1700

Data Index: 6365066 (Open Web Text)

Max Activating Token Index: 220

Text #13

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6433. Min Act: -0.1700

Data Index: 5626963 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6427. Min Act: -0.1700

Data Index: 1694499 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6713. Min Act: -0.1700

Data Index: 543501 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6451. Min Act: -0.1700

Data Index: 3393179 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6038. Min Act: -0.1700

Data Index: 6875611 (Open Web Text)

Max Activating Token Index: 125

Text #18

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.6476. Min Act: -0.1700

Data Index: 8683527 (Open Web Text)

Max Activating Token Index: 395

Text #19

Max Range: 6.1336. Min Range: -6.1336

Max Act: 5.5596. Min Act: -0.1700

Data Index: 6508891 (Open Web Text)

Max Activating Token Index: 235