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

Dataset: Open Web Text

Neuron 1580 in Layer 2

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: 3.5570. Min Range: -3.5570

Max Act: 3.5570. Min Act: -0.1700

Data Index: 4319718 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.5035. Min Act: -0.1700

Data Index: 4459136 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.4599. Min Act: -0.1700

Data Index: 3031832 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3825. Min Act: -0.1700

Data Index: 4825512 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.3253. Min Act: -0.1700

Data Index: 7992345 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2976. Min Act: -0.1700

Data Index: 875641 (Open Web Text)

Max Activating Token Index: 217

Text #6

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2975. Min Act: -0.1700

Data Index: 3950277 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2791. Min Act: -0.1700

Data Index: 6182228 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2804. Min Act: -0.1700

Data Index: 7911495 (Open Web Text)

Max Activating Token Index: 78

Text #9

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2723. Min Act: -0.1700

Data Index: 5679111 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2654. Min Act: -0.1700

Data Index: 8321541 (Open Web Text)

Max Activating Token Index: 151

Text #11

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2565. Min Act: -0.1700

Data Index: 7179681 (Open Web Text)

Max Activating Token Index: 41

Text #12

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2362. Min Act: -0.1700

Data Index: 2893643 (Open Web Text)

Max Activating Token Index: 69

Text #13

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2604. Min Act: -0.1700

Data Index: 4229868 (Open Web Text)

Max Activating Token Index: 819

Text #14

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2520. Min Act: -0.1700

Data Index: 1003629 (Open Web Text)

Max Activating Token Index: 688

Text #15

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2276. Min Act: -0.1700

Data Index: 3925607 (Open Web Text)

Max Activating Token Index: 165

Text #16

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2423. Min Act: -0.1700

Data Index: 8107296 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2259. Min Act: -0.1700

Data Index: 2647290 (Open Web Text)

Max Activating Token Index: 264

Text #18

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2344. Min Act: -0.1700

Data Index: 7762931 (Open Web Text)

Max Activating Token Index: 342

Text #19

Max Range: 3.5570. Min Range: -3.5570

Max Act: 3.2315. Min Act: -0.1700

Data Index: 8258335 (Open Web Text)

Max Activating Token Index: 204