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

Dataset: Open Web Text

Neuron 349 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: 1.7518. Min Range: -1.7518

Max Act: 1.7471. Min Act: -0.1700

Data Index: 8047853 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7518. Min Act: -0.1700

Data Index: 7948272 (Open Web Text)

Max Activating Token Index: 996

Text #2

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7379. Min Act: -0.1671

Data Index: 4112099 (Open Web Text)

Max Activating Token Index: 85

Text #3

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7344. Min Act: -0.1700

Data Index: 1572734 (Open Web Text)

Max Activating Token Index: 662

Text #4

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7143. Min Act: -0.1700

Data Index: 187650 (Open Web Text)

Max Activating Token Index: 490

Text #5

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6991. Min Act: -0.1699

Data Index: 6063899 (Open Web Text)

Max Activating Token Index: 642

Text #6

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7036. Min Act: -0.1700

Data Index: 3698153 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6892. Min Act: -0.1700

Data Index: 7849145 (Open Web Text)

Max Activating Token Index: 767

Text #8

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7007. Min Act: -0.1700

Data Index: 2049560 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6968. Min Act: -0.1697

Data Index: 2422251 (Open Web Text)

Max Activating Token Index: 702

Text #10

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.7001. Min Act: -0.1700

Data Index: 7570666 (Open Web Text)

Max Activating Token Index: 467

Text #11

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6895. Min Act: -0.1700

Data Index: 7915071 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6885. Min Act: -0.1700

Data Index: 5660632 (Open Web Text)

Max Activating Token Index: 53

Text #13

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6935. Min Act: -0.1700

Data Index: 5155199 (Open Web Text)

Max Activating Token Index: 604

Text #14

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6816. Min Act: -0.1700

Data Index: 4648190 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6892. Min Act: -0.1700

Data Index: 4428435 (Open Web Text)

Max Activating Token Index: 587

Text #16

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6786. Min Act: -0.1679

Data Index: 6166690 (Open Web Text)

Max Activating Token Index: 101

Text #17

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6766. Min Act: -0.1700

Data Index: 5532963 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6793. Min Act: -0.1700

Data Index: 1097075 (Open Web Text)

Max Activating Token Index: 159

Text #19

Max Range: 1.7518. Min Range: -1.7518

Max Act: 1.6752. Min Act: -0.1700

Data Index: 3735408 (Open Web Text)

Max Activating Token Index: 552