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

Dataset: Open Web Text

Neuron 1127 in Layer 6

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: 4.4956. Min Range: -4.4956

Max Act: 4.4956. Min Act: -0.1700

Data Index: 4372400 (Open Web Text)

Max Activating Token Index: 174

Text #1

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.2014. Min Act: -0.1700

Data Index: 1606778 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.1822. Min Act: -0.1700

Data Index: 1971730 (Open Web Text)

Max Activating Token Index: 280

Text #3

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.1080. Min Act: -0.1700

Data Index: 7466775 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0949. Min Act: -0.1700

Data Index: 2543540 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0602. Min Act: -0.1700

Data Index: 6017402 (Open Web Text)

Max Activating Token Index: 83

Text #6

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0385. Min Act: -0.1700

Data Index: 8514824 (Open Web Text)

Max Activating Token Index: 775

Text #7

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0657. Min Act: -0.1700

Data Index: 5522518 (Open Web Text)

Max Activating Token Index: 298

Text #8

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0485. Min Act: -0.1700

Data Index: 2509023 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0317. Min Act: -0.1700

Data Index: 2636152 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0253. Min Act: -0.1700

Data Index: 6051383 (Open Web Text)

Max Activating Token Index: 585

Text #11

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0290. Min Act: -0.1700

Data Index: 5928459 (Open Web Text)

Max Activating Token Index: 88

Text #12

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0294. Min Act: -0.1700

Data Index: 80313 (Open Web Text)

Max Activating Token Index: 842

Text #13

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9965. Min Act: -0.1700

Data Index: 5835637 (Open Web Text)

Max Activating Token Index: 396

Text #14

Max Range: 4.4956. Min Range: -4.4956

Max Act: 4.0264. Min Act: -0.1700

Data Index: 1821296 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9442. Min Act: -0.1700

Data Index: 1817922 (Open Web Text)

Max Activating Token Index: 617

Text #16

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9987. Min Act: -0.1700

Data Index: 6162740 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9736. Min Act: -0.1700

Data Index: 4842684 (Open Web Text)

Max Activating Token Index: 546

Text #18

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9740. Min Act: -0.1700

Data Index: 2063630 (Open Web Text)

Max Activating Token Index: 756

Text #19

Max Range: 4.4956. Min Range: -4.4956

Max Act: 3.9829. Min Act: -0.1700

Data Index: 7021772 (Open Web Text)

Max Activating Token Index: 770