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

Dataset: Open Web Text

Neuron 152 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: 3.3177. Min Range: -3.3177

Max Act: 3.2976. Min Act: -0.1700

Data Index: 2805609 (Open Web Text)

Max Activating Token Index: 528

Text #1

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.3177. Min Act: -0.1700

Data Index: 3978413 (Open Web Text)

Max Activating Token Index: 817

Text #2

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2973. Min Act: -0.1700

Data Index: 722325 (Open Web Text)

Max Activating Token Index: 179

Text #3

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2711. Min Act: -0.1700

Data Index: 3649709 (Open Web Text)

Max Activating Token Index: 476

Text #4

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2890. Min Act: -0.1700

Data Index: 1504562 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2226. Min Act: -0.1700

Data Index: 7804716 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2168. Min Act: -0.1700

Data Index: 2535810 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2211. Min Act: -0.1700

Data Index: 7043425 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1911680 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.2097. Min Act: -0.1700

Data Index: 1953236 (Open Web Text)

Max Activating Token Index: 323

Text #10

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1909. Min Act: -0.1700

Data Index: 5134104 (Open Web Text)

Max Activating Token Index: 206

Text #11

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1753. Min Act: -0.1700

Data Index: 3114896 (Open Web Text)

Max Activating Token Index: 74

Text #12

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1496. Min Act: -0.1700

Data Index: 4794193 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1648. Min Act: -0.1700

Data Index: 3943967 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1578. Min Act: -0.1700

Data Index: 3348917 (Open Web Text)

Max Activating Token Index: 110

Text #15

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1239. Min Act: -0.1700

Data Index: 2230047 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1353. Min Act: -0.1700

Data Index: 8469652 (Open Web Text)

Max Activating Token Index: 838

Text #17

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1450. Min Act: -0.1700

Data Index: 2535811 (Open Web Text)

Max Activating Token Index: 53

Text #18

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1338. Min Act: -0.1700

Data Index: 8208571 (Open Web Text)

Max Activating Token Index: 779

Text #19

Max Range: 3.3177. Min Range: -3.3177

Max Act: 3.1416. Min Act: -0.1700

Data Index: 1281170 (Open Web Text)

Max Activating Token Index: 60