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

Dataset: Open Web Text

Neuron 865 in Layer 0

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: 3.4385. Min Range: -3.4385

Max Act: 3.4385. Min Act: -0.1700

Data Index: 2255043 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1085540 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.4126. Min Act: -0.1700

Data Index: 8809380 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3514. Min Act: -0.1700

Data Index: 4506160 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3569. Min Act: -0.1700

Data Index: 4240948 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3292. Min Act: -0.1700

Data Index: 106015 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3365. Min Act: -0.1700

Data Index: 7999552 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3245. Min Act: -0.1700

Data Index: 6662705 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3181. Min Act: -0.1700

Data Index: 935345 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3038. Min Act: -0.1700

Data Index: 280707 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1624550 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2957. Min Act: -0.1700

Data Index: 2269116 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2793. Min Act: -0.1700

Data Index: 8662872 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2664. Min Act: -0.1700

Data Index: 3281542 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2536. Min Act: -0.1700

Data Index: 175468 (Open Web Text)

Max Activating Token Index: 18

Text #15

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2442. Min Act: -0.1700

Data Index: 5257742 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2574. Min Act: -0.1700

Data Index: 5479226 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2504. Min Act: -0.1700

Data Index: 265123 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2491. Min Act: -0.1700

Data Index: 6202129 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.4385. Min Range: -3.4385

Max Act: 3.2364. Min Act: -0.1700

Data Index: 1553968 (Open Web Text)

Max Activating Token Index: 5