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

Dataset: Open Web Text

Neuron 298 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: 4.2194. Min Range: -4.2194

Max Act: 4.2194. Min Act: -0.1700

Data Index: 3457515 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 4.2194. Min Range: -4.2194

Max Act: 4.1340. Min Act: -0.1700

Data Index: 7117279 (Open Web Text)

Max Activating Token Index: 123

Text #2

Max Range: 4.2194. Min Range: -4.2194

Max Act: 4.0735. Min Act: -0.1700

Data Index: 1307870 (Open Web Text)

Max Activating Token Index: 781

Text #3

Max Range: 4.2194. Min Range: -4.2194

Max Act: 4.0288. Min Act: -0.1700

Data Index: 7316156 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 4.2194. Min Range: -4.2194

Max Act: 4.0227. Min Act: -0.1700

Data Index: 2015258 (Open Web Text)

Max Activating Token Index: 242

Text #5

Max Range: 4.2194. Min Range: -4.2194

Max Act: 4.0106. Min Act: -0.1700

Data Index: 1307871 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9813. Min Act: -0.1700

Data Index: 1374690 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9967. Min Act: -0.1700

Data Index: 62958 (Open Web Text)

Max Activating Token Index: 113

Text #8

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9478. Min Act: -0.1700

Data Index: 3755899 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9260. Min Act: -0.1700

Data Index: 4858683 (Open Web Text)

Max Activating Token Index: 400

Text #10

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9703. Min Act: -0.1700

Data Index: 319842 (Open Web Text)

Max Activating Token Index: 610

Text #11

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9396. Min Act: -0.1700

Data Index: 47688 (Open Web Text)

Max Activating Token Index: 544

Text #12

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9130. Min Act: -0.1700

Data Index: 6807238 (Open Web Text)

Max Activating Token Index: 416

Text #13

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9181. Min Act: -0.1700

Data Index: 855831 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9479. Min Act: -0.1700

Data Index: 4099334 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9193. Min Act: -0.1700

Data Index: 8510891 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.8976. Min Act: -0.1700

Data Index: 3715259 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.9094. Min Act: -0.1700

Data Index: 1229662 (Open Web Text)

Max Activating Token Index: 95

Text #18

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.8725. Min Act: -0.1700

Data Index: 1142587 (Open Web Text)

Max Activating Token Index: 125

Text #19

Max Range: 4.2194. Min Range: -4.2194

Max Act: 3.8987. Min Act: -0.1700

Data Index: 5549052 (Open Web Text)

Max Activating Token Index: 142