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

Dataset: Open Web Text

Neuron 612 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: 4.5385. Min Range: -4.5385

Max Act: 4.5385. Min Act: -0.1700

Data Index: 1557859 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4921. Min Act: -0.1700

Data Index: 50312 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4772. Min Act: -0.1700

Data Index: 8401676 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.5066. Min Act: -0.1700

Data Index: 7935432 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4665. Min Act: -0.1700

Data Index: 5960462 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4472. Min Act: -0.1700

Data Index: 7712189 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4338. Min Act: -0.1700

Data Index: 6600243 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4222. Min Act: -0.1700

Data Index: 3038527 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4325. Min Act: -0.1700

Data Index: 147953 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4365. Min Act: -0.1700

Data Index: 5691438 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4326. Min Act: -0.1700

Data Index: 5664648 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4212. Min Act: -0.1700

Data Index: 5316498 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4206. Min Act: -0.1700

Data Index: 6813367 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4005. Min Act: -0.1700

Data Index: 402064 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4101. Min Act: -0.1700

Data Index: 7653350 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.3879. Min Act: -0.1700

Data Index: 5808033 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.3977. Min Act: -0.1700

Data Index: 5132730 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.4092. Min Act: -0.1700

Data Index: 3728072 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.3920. Min Act: -0.1700

Data Index: 7006614 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.5385. Min Range: -4.5385

Max Act: 4.3795. Min Act: -0.1700

Data Index: 6256476 (Open Web Text)

Max Activating Token Index: 5