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

Dataset: Open Web Text

Neuron 2762 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: 3.4273. Min Range: -3.4273

Max Act: 3.4273. Min Act: -0.1700

Data Index: 2328359 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.3662. Min Act: -0.1700

Data Index: 4914058 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.3191. Min Act: -0.1700

Data Index: 3250865 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2980. Min Act: -0.1700

Data Index: 5105000 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.3043. Min Act: -0.1700

Data Index: 3154068 (Open Web Text)

Max Activating Token Index: 815

Text #5

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2759. Min Act: -0.1700

Data Index: 745810 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2982. Min Act: -0.1700

Data Index: 2302607 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2548. Min Act: -0.1700

Data Index: 6025639 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2520. Min Act: -0.1700

Data Index: 5892076 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2361. Min Act: -0.1700

Data Index: 1448168 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2257. Min Act: -0.1700

Data Index: 2935472 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2442. Min Act: -0.1700

Data Index: 6425654 (Open Web Text)

Max Activating Token Index: 29

Text #12

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2219. Min Act: -0.1700

Data Index: 5553853 (Open Web Text)

Max Activating Token Index: 634

Text #13

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2229. Min Act: -0.1700

Data Index: 6425797 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2155. Min Act: -0.1700

Data Index: 2135327 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2061. Min Act: -0.1700

Data Index: 3250149 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2187. Min Act: -0.1700

Data Index: 2069676 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.2132. Min Act: -0.1700

Data Index: 6960958 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.1935. Min Act: -0.1700

Data Index: 3823562 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.4273. Min Range: -3.4273

Max Act: 3.1955. Min Act: -0.1700

Data Index: 1770356 (Open Web Text)

Max Activating Token Index: 5