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

Dataset: Open Web Text

Neuron 86 in Layer 1

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: 2.4217. Min Range: -2.4217

Max Act: 2.4217. Min Act: -0.1700

Data Index: 1706121 (Open Web Text)

Max Activating Token Index: 365

Text #1

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2601. Min Act: -0.1700

Data Index: 5057266 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2513. Min Act: -0.1700

Data Index: 1410466 (Open Web Text)

Max Activating Token Index: 516

Text #3

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2536. Min Act: -0.1700

Data Index: 419742 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2387. Min Act: -0.1700

Data Index: 7396117 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2267. Min Act: -0.1700

Data Index: 6076203 (Open Web Text)

Max Activating Token Index: 177

Text #6

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2385. Min Act: -0.1700

Data Index: 8687627 (Open Web Text)

Max Activating Token Index: 462

Text #7

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2339. Min Act: -0.1700

Data Index: 534295 (Open Web Text)

Max Activating Token Index: 637

Text #8

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2278. Min Act: -0.1700

Data Index: 8547977 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2315. Min Act: -0.1700

Data Index: 5589252 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2336. Min Act: -0.1700

Data Index: 6150437 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2140. Min Act: -0.1700

Data Index: 7931212 (Open Web Text)

Max Activating Token Index: 95

Text #12

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2060. Min Act: -0.1700

Data Index: 7818109 (Open Web Text)

Max Activating Token Index: 66

Text #13

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.1898. Min Act: -0.1690

Data Index: 8385726 (Open Web Text)

Max Activating Token Index: 901

Text #14

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.1944. Min Act: -0.1700

Data Index: 3878708 (Open Web Text)

Max Activating Token Index: 370

Text #15

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2025. Min Act: -0.1700

Data Index: 1466237 (Open Web Text)

Max Activating Token Index: 868

Text #16

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.1988. Min Act: -0.1700

Data Index: 4708811 (Open Web Text)

Max Activating Token Index: 732

Text #17

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.2075. Min Act: -0.1700

Data Index: 7435341 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.1890. Min Act: -0.1700

Data Index: 1131429 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 2.4217. Min Range: -2.4217

Max Act: 2.1894. Min Act: -0.1700

Data Index: 4269869 (Open Web Text)

Max Activating Token Index: 97