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

Dataset: Open Web Text

Neuron 2986 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: 4.4030. Min Range: -4.4030

Max Act: 4.4030. Min Act: -0.1700

Data Index: 5940307 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.3554. Min Act: -0.1700

Data Index: 5993063 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.2856. Min Act: -0.1700

Data Index: 7440936 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.2312. Min Act: -0.1700

Data Index: 7582125 (Open Web Text)

Max Activating Token Index: 279

Text #4

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.2094. Min Act: -0.1700

Data Index: 7022788 (Open Web Text)

Max Activating Token Index: 907

Text #5

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1991. Min Act: -0.1700

Data Index: 2529051 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1860. Min Act: -0.1700

Data Index: 2518606 (Open Web Text)

Max Activating Token Index: 300

Text #7

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1864. Min Act: -0.1700

Data Index: 4092186 (Open Web Text)

Max Activating Token Index: 554

Text #8

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.0836. Min Act: -0.1700

Data Index: 5083020 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.2039. Min Act: -0.1700

Data Index: 7812644 (Open Web Text)

Max Activating Token Index: 792

Text #10

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1572. Min Act: -0.1700

Data Index: 3458536 (Open Web Text)

Max Activating Token Index: 575

Text #11

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1484. Min Act: -0.1700

Data Index: 539573 (Open Web Text)

Max Activating Token Index: 471

Text #12

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1835. Min Act: -0.1700

Data Index: 4282910 (Open Web Text)

Max Activating Token Index: 900

Text #13

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1777. Min Act: -0.1700

Data Index: 5796353 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1225. Min Act: -0.1700

Data Index: 7010102 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1377. Min Act: -0.1700

Data Index: 6773698 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1623. Min Act: -0.1700

Data Index: 6181116 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1276. Min Act: -0.1700

Data Index: 1017493 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.1336. Min Act: -0.1700

Data Index: 5796354 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 4.4030. Min Range: -4.4030

Max Act: 4.0937. Min Act: -0.1700

Data Index: 282424 (Open Web Text)

Max Activating Token Index: 135