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

Dataset: Open Web Text

Neuron 910 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: 1.3073. Min Range: -1.3073

Max Act: 1.3073. Min Act: -0.1700

Data Index: 4413681 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.3046. Min Act: -0.1700

Data Index: 6920453 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2894. Min Act: -0.1700

Data Index: 4473705 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2791. Min Act: -0.1700

Data Index: 6918473 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2742. Min Act: -0.1700

Data Index: 478279 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2599. Min Act: -0.1700

Data Index: 3302845 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2669. Min Act: -0.1700

Data Index: 5342638 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2526. Min Act: -0.1700

Data Index: 489345 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2542. Min Act: -0.1700

Data Index: 4164429 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2451. Min Act: -0.1700

Data Index: 2890930 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2539. Min Act: -0.1700

Data Index: 516440 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2459. Min Act: -0.1700

Data Index: 7282534 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2407. Min Act: -0.1700

Data Index: 7915211 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2446. Min Act: -0.1700

Data Index: 7395863 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2393. Min Act: -0.1700

Data Index: 5412809 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2466. Min Act: -0.1700

Data Index: 1182569 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2439. Min Act: -0.1700

Data Index: 7883230 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2310. Min Act: -0.1700

Data Index: 2406373 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2307. Min Act: -0.1700

Data Index: 4710041 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.3073. Min Range: -1.3073

Max Act: 1.2313. Min Act: -0.1700

Data Index: 4678211 (Open Web Text)

Max Activating Token Index: 5