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

Dataset: Open Web Text

Neuron 2843 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: 3.3263. Min Range: -3.3263

Max Act: 3.3241. Min Act: -0.1700

Data Index: 5675850 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.3263. Min Act: -0.1700

Data Index: 266747 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.3165. Min Act: -0.1700

Data Index: 8378660 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2975. Min Act: -0.1700

Data Index: 8401948 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2977. Min Act: -0.1700

Data Index: 3296571 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2975. Min Act: -0.1700

Data Index: 1144957 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2979. Min Act: -0.1700

Data Index: 5965394 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2975. Min Act: -0.1700

Data Index: 4170629 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2864. Min Act: -0.1700

Data Index: 6000971 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2864. Min Act: -0.1700

Data Index: 8418878 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2692. Min Act: -0.1700

Data Index: 6895102 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2460. Min Act: -0.1700

Data Index: 4692749 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2605. Min Act: -0.1700

Data Index: 7938671 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2570. Min Act: -0.1700

Data Index: 2322200 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2635. Min Act: -0.1700

Data Index: 7623864 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2412. Min Act: -0.1700

Data Index: 4594954 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2266. Min Act: -0.1700

Data Index: 4188889 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2440. Min Act: -0.1700

Data Index: 5263543 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2331. Min Act: -0.1700

Data Index: 7058449 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.3263. Min Range: -3.3263

Max Act: 3.2150. Min Act: -0.1700

Data Index: 389255 (Open Web Text)

Max Activating Token Index: 3