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

Dataset: Open Web Text

Neuron 1686 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: 4.9874. Min Range: -4.9874

Max Act: 4.9874. Min Act: -0.1700

Data Index: 5416405 (Open Web Text)

Max Activating Token Index: 19

Text #1

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.9091. Min Act: -0.1700

Data Index: 8672070 (Open Web Text)

Max Activating Token Index: 242

Text #2

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8917. Min Act: -0.1700

Data Index: 5658480 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8711. Min Act: -0.1700

Data Index: 4832186 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8638. Min Act: -0.1700

Data Index: 1476918 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8615. Min Act: -0.1700

Data Index: 4785989 (Open Web Text)

Max Activating Token Index: 210

Text #6

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8591. Min Act: -0.1700

Data Index: 8535292 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8671. Min Act: -0.1700

Data Index: 7151297 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8395. Min Act: -0.1700

Data Index: 2187906 (Open Web Text)

Max Activating Token Index: 599

Text #9

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8179. Min Act: -0.1700

Data Index: 8602346 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8339. Min Act: -0.1700

Data Index: 6739562 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.8135. Min Act: -0.1700

Data Index: 5416408 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7683. Min Act: -0.1700

Data Index: 511942 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7707. Min Act: -0.1700

Data Index: 8387684 (Open Web Text)

Max Activating Token Index: 37

Text #14

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7653. Min Act: -0.1700

Data Index: 1592023 (Open Web Text)

Max Activating Token Index: 487

Text #15

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7664. Min Act: -0.1700

Data Index: 5211301 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7197. Min Act: -0.1700

Data Index: 2027767 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7219. Min Act: -0.1700

Data Index: 410800 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.7065. Min Act: -0.1700

Data Index: 2245278 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 4.9874. Min Range: -4.9874

Max Act: 4.6679. Min Act: -0.1700

Data Index: 7727599 (Open Web Text)

Max Activating Token Index: 773