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

Dataset: Open Web Text

Neuron 2524 in Layer 0

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: 4.0780. Min Range: -4.0780

Max Act: 4.0780. Min Act: -0.1700

Data Index: 5895443 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 4.0780. Min Range: -4.0780

Max Act: 4.0283. Min Act: -0.1700

Data Index: 4406938 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9827. Min Act: -0.1700

Data Index: 6032957 (Open Web Text)

Max Activating Token Index: 21

Text #3

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9591. Min Act: -0.1700

Data Index: 2909658 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 2365977 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9462. Min Act: -0.1700

Data Index: 2365580 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9431. Min Act: -0.1700

Data Index: 8025727 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9391. Min Act: -0.1700

Data Index: 3037772 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9342. Min Act: -0.1700

Data Index: 4150380 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 7572092 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 6391373 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 6199906 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 6191799 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 5355297 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9510. Min Act: -0.1700

Data Index: 4665514 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9069. Min Act: -0.1700

Data Index: 3176836 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9072. Min Act: -0.1700

Data Index: 348556 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9386. Min Act: -0.1700

Data Index: 3260402 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9072. Min Act: -0.1700

Data Index: 3431578 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.0780. Min Range: -4.0780

Max Act: 3.9072. Min Act: -0.1700

Data Index: 3922969 (Open Web Text)

Max Activating Token Index: 3