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

Dataset: Open Web Text

Neuron 1809 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: 3.4097. Min Range: -3.4097

Max Act: 3.4097. Min Act: -0.1700

Data Index: 68621 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.3710. Min Act: -0.1700

Data Index: 2311096 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.3693. Min Act: -0.1700

Data Index: 5394545 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.3067. Min Act: -0.1700

Data Index: 1752230 (Open Web Text)

Max Activating Token Index: 965

Text #4

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2888. Min Act: -0.1700

Data Index: 1601902 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2692. Min Act: -0.1700

Data Index: 2634399 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2896. Min Act: -0.1700

Data Index: 5631329 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2798. Min Act: -0.1700

Data Index: 5727518 (Open Web Text)

Max Activating Token Index: 100

Text #8

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2672. Min Act: -0.1700

Data Index: 7908368 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2735. Min Act: -0.1700

Data Index: 1672801 (Open Web Text)

Max Activating Token Index: 298

Text #10

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2730. Min Act: -0.1700

Data Index: 2311089 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2496. Min Act: -0.1700

Data Index: 2061975 (Open Web Text)

Max Activating Token Index: 448

Text #12

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2413. Min Act: -0.1700

Data Index: 7076022 (Open Web Text)

Max Activating Token Index: 156

Text #13

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2405. Min Act: -0.1700

Data Index: 1838774 (Open Web Text)

Max Activating Token Index: 117

Text #14

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2264. Min Act: -0.1700

Data Index: 6737766 (Open Web Text)

Max Activating Token Index: 616

Text #15

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2225. Min Act: -0.1700

Data Index: 4994481 (Open Web Text)

Max Activating Token Index: 409

Text #16

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2013. Min Act: -0.1700

Data Index: 527539 (Open Web Text)

Max Activating Token Index: 253

Text #17

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2131. Min Act: -0.1700

Data Index: 4769489 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.1913. Min Act: -0.1700

Data Index: 144738 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 3.4097. Min Range: -3.4097

Max Act: 3.2022. Min Act: -0.1700

Data Index: 6058873 (Open Web Text)

Max Activating Token Index: 198