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

Dataset: Open Web Text

Neuron 1851 in Layer 2

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: 4.7637. Min Range: -4.7637

Max Act: 4.7637. Min Act: -0.1700

Data Index: 3026197 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6661. Min Act: -0.1700

Data Index: 5362694 (Open Web Text)

Max Activating Token Index: 979

Text #2

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6602. Min Act: -0.1700

Data Index: 6466902 (Open Web Text)

Max Activating Token Index: 884

Text #3

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6781. Min Act: -0.1700

Data Index: 6974348 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6543. Min Act: -0.1700

Data Index: 3975802 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6601. Min Act: -0.1700

Data Index: 3093656 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6621. Min Act: -0.1700

Data Index: 5480964 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6367. Min Act: -0.1700

Data Index: 1873457 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6540. Min Act: -0.1700

Data Index: 5264014 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6394. Min Act: -0.1700

Data Index: 1977014 (Open Web Text)

Max Activating Token Index: 544

Text #10

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6510. Min Act: -0.1700

Data Index: 2425553 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6347. Min Act: -0.1700

Data Index: 8825136 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6612. Min Act: -0.1700

Data Index: 485171 (Open Web Text)

Max Activating Token Index: 510

Text #13

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6175. Min Act: -0.1700

Data Index: 4752132 (Open Web Text)

Max Activating Token Index: 690

Text #14

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.5968. Min Act: -0.1700

Data Index: 947552 (Open Web Text)

Max Activating Token Index: 581

Text #15

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.5990. Min Act: -0.1700

Data Index: 4755300 (Open Web Text)

Max Activating Token Index: 96

Text #16

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6233. Min Act: -0.1700

Data Index: 2430184 (Open Web Text)

Max Activating Token Index: 753

Text #17

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6086. Min Act: -0.1700

Data Index: 4873926 (Open Web Text)

Max Activating Token Index: 635

Text #18

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6120. Min Act: -0.1700

Data Index: 5067534 (Open Web Text)

Max Activating Token Index: 100

Text #19

Max Range: 4.7637. Min Range: -4.7637

Max Act: 4.6025. Min Act: -0.1700

Data Index: 3127128 (Open Web Text)

Max Activating Token Index: 366