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

Dataset: Open Web Text

Neuron 43 in Layer 3

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: 3.3160. Min Range: -3.3160

Max Act: 3.3160. Min Act: -0.1700

Data Index: 5844667 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.2864. Min Act: -0.1700

Data Index: 2276283 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.2601. Min Act: -0.1700

Data Index: 3752500 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.2258. Min Act: -0.1700

Data Index: 8418196 (Open Web Text)

Max Activating Token Index: 338

Text #4

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1980. Min Act: -0.1700

Data Index: 4807315 (Open Web Text)

Max Activating Token Index: 501

Text #5

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.2057. Min Act: -0.1700

Data Index: 7039381 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1822. Min Act: -0.1700

Data Index: 5380564 (Open Web Text)

Max Activating Token Index: 220

Text #7

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1872. Min Act: -0.1700

Data Index: 6175244 (Open Web Text)

Max Activating Token Index: 709

Text #8

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1713. Min Act: -0.1700

Data Index: 6900235 (Open Web Text)

Max Activating Token Index: 179

Text #9

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1752. Min Act: -0.1700

Data Index: 1119289 (Open Web Text)

Max Activating Token Index: 183

Text #10

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1094965 (Open Web Text)

Max Activating Token Index: 490

Text #11

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1830. Min Act: -0.1700

Data Index: 7292399 (Open Web Text)

Max Activating Token Index: 391

Text #12

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1701. Min Act: -0.1700

Data Index: 4479577 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1510. Min Act: -0.1700

Data Index: 8206399 (Open Web Text)

Max Activating Token Index: 751

Text #14

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1573. Min Act: -0.1700

Data Index: 2825938 (Open Web Text)

Max Activating Token Index: 136

Text #15

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1617. Min Act: -0.1700

Data Index: 2182714 (Open Web Text)

Max Activating Token Index: 693

Text #16

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1766. Min Act: -0.1700

Data Index: 108267 (Open Web Text)

Max Activating Token Index: 121

Text #17

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1575. Min Act: -0.1700

Data Index: 2018846 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1540. Min Act: -0.1700

Data Index: 6271388 (Open Web Text)

Max Activating Token Index: 507

Text #19

Max Range: 3.3160. Min Range: -3.3160

Max Act: 3.1545. Min Act: -0.1700

Data Index: 6075696 (Open Web Text)

Max Activating Token Index: 733