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

Dataset: Open Web Text

Neuron 528 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: 2.2576. Min Range: -2.2576

Max Act: 2.2576. Min Act: -0.1700

Data Index: 5485097 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.2212. Min Act: -0.1700

Data Index: 3771322 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.2141. Min Act: -0.1700

Data Index: 198850 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.2026. Min Act: -0.1700

Data Index: 5395740 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.2057. Min Act: -0.1700

Data Index: 71829 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.2017. Min Act: -0.1700

Data Index: 8058667 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1794. Min Act: -0.1700

Data Index: 4467909 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 4387208 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 1541995 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 2674111 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 6594692 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 6079542 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 3472527 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 516905 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 3298803 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 238480 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 3218389 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1476. Min Act: -0.1700

Data Index: 4962302 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1409. Min Act: -0.1700

Data Index: 8366070 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.2576. Min Range: -2.2576

Max Act: 2.1351. Min Act: -0.1700

Data Index: 7288442 (Open Web Text)

Max Activating Token Index: 3