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

Dataset: Open Web Text

Neuron 249 in Layer 6

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: 3.9065. Min Range: -3.9065

Max Act: 3.9065. Min Act: -0.1700

Data Index: 8245158 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.8207. Min Act: -0.1700

Data Index: 7952976 (Open Web Text)

Max Activating Token Index: 416

Text #2

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.8334. Min Act: -0.1700

Data Index: 1893448 (Open Web Text)

Max Activating Token Index: 954

Text #3

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.8046. Min Act: -0.1700

Data Index: 3359832 (Open Web Text)

Max Activating Token Index: 301

Text #4

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7695. Min Act: -0.1700

Data Index: 6038216 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7528. Min Act: -0.1700

Data Index: 8646359 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7342. Min Act: -0.1700

Data Index: 2982009 (Open Web Text)

Max Activating Token Index: 90

Text #7

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7183. Min Act: -0.1700

Data Index: 176433 (Open Web Text)

Max Activating Token Index: 97

Text #8

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7225. Min Act: -0.1700

Data Index: 688703 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7228. Min Act: -0.1700

Data Index: 2982005 (Open Web Text)

Max Activating Token Index: 147

Text #10

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.7021. Min Act: -0.1700

Data Index: 8479461 (Open Web Text)

Max Activating Token Index: 941

Text #11

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6846. Min Act: -0.1700

Data Index: 2981997 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6944. Min Act: -0.1700

Data Index: 5310635 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6827. Min Act: -0.1700

Data Index: 8239702 (Open Web Text)

Max Activating Token Index: 300

Text #14

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6843. Min Act: -0.1700

Data Index: 3292818 (Open Web Text)

Max Activating Token Index: 73

Text #15

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6655. Min Act: -0.1700

Data Index: 6880082 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6775. Min Act: -0.1700

Data Index: 2783939 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6467. Min Act: -0.1700

Data Index: 2390036 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6252. Min Act: -0.1700

Data Index: 176442 (Open Web Text)

Max Activating Token Index: 86

Text #19

Max Range: 3.9065. Min Range: -3.9065

Max Act: 3.6111. Min Act: -0.1700

Data Index: 613278 (Open Web Text)

Max Activating Token Index: 58