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

Dataset: Open Web Text

Neuron 900 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: 3.3395. Min Range: -3.3395

Max Act: 3.3395. Min Act: -0.1700

Data Index: 2015489 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.3108. Min Act: -0.1700

Data Index: 286378 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.3164. Min Act: -0.1700

Data Index: 400214 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2900. Min Act: -0.1700

Data Index: 5930958 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2777. Min Act: -0.1700

Data Index: 4264357 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2849. Min Act: -0.1700

Data Index: 6096598 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2682. Min Act: -0.1700

Data Index: 8681160 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2639. Min Act: -0.1700

Data Index: 612587 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2453. Min Act: -0.1700

Data Index: 7271776 (Open Web Text)

Max Activating Token Index: 28

Text #9

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2609. Min Act: -0.1700

Data Index: 7823926 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2454. Min Act: -0.1700

Data Index: 3705145 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2500. Min Act: -0.1700

Data Index: 6368173 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2308. Min Act: -0.1700

Data Index: 3641825 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2375. Min Act: -0.1700

Data Index: 6814609 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2407. Min Act: -0.1700

Data Index: 6795551 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2323. Min Act: -0.1700

Data Index: 368232 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2288. Min Act: -0.1700

Data Index: 1234097 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2398. Min Act: -0.1700

Data Index: 3480098 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2274. Min Act: -0.1700

Data Index: 3258242 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3395. Min Range: -3.3395

Max Act: 3.2326. Min Act: -0.1700

Data Index: 5691834 (Open Web Text)

Max Activating Token Index: 9