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

Dataset: Open Web Text

Neuron 120 in Layer 5

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: 3.2884. Min Range: -3.2884

Max Act: 3.2884. Min Act: -0.1700

Data Index: 8298864 (Open Web Text)

Max Activating Token Index: 396

Text #1

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.2073. Min Act: -0.1700

Data Index: 6243970 (Open Web Text)

Max Activating Token Index: 151

Text #2

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.2253. Min Act: -0.1700

Data Index: 1859683 (Open Web Text)

Max Activating Token Index: 117

Text #3

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.2194. Min Act: -0.1700

Data Index: 2297393 (Open Web Text)

Max Activating Token Index: 211

Text #4

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1252. Min Act: -0.1700

Data Index: 7755893 (Open Web Text)

Max Activating Token Index: 125

Text #5

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1255. Min Act: -0.1700

Data Index: 2672147 (Open Web Text)

Max Activating Token Index: 105

Text #6

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1081. Min Act: -0.1700

Data Index: 4010616 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1405. Min Act: -0.1700

Data Index: 459121 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1024. Min Act: -0.1700

Data Index: 7672901 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.1119. Min Act: -0.1700

Data Index: 2318490 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0729. Min Act: -0.1700

Data Index: 5928405 (Open Web Text)

Max Activating Token Index: 557

Text #11

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0988. Min Act: -0.1700

Data Index: 2570470 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0971. Min Act: -0.1700

Data Index: 2169650 (Open Web Text)

Max Activating Token Index: 992

Text #13

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0884. Min Act: -0.1700

Data Index: 5457096 (Open Web Text)

Max Activating Token Index: 174

Text #14

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0702. Min Act: -0.1700

Data Index: 6500005 (Open Web Text)

Max Activating Token Index: 192

Text #15

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0702. Min Act: -0.1700

Data Index: 2276517 (Open Web Text)

Max Activating Token Index: 575

Text #16

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0855. Min Act: -0.1700

Data Index: 1421950 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0449. Min Act: -0.1700

Data Index: 6589345 (Open Web Text)

Max Activating Token Index: 390

Text #18

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0776. Min Act: -0.1700

Data Index: 8146899 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 3.2884. Min Range: -3.2884

Max Act: 3.0358. Min Act: -0.1700

Data Index: 929779 (Open Web Text)

Max Activating Token Index: 881