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

Dataset: Open Web Text

Neuron 1981 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: 5.7667. Min Range: -5.7667

Max Act: 5.7667. Min Act: -0.1700

Data Index: 71973 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.7626. Min Act: -0.1700

Data Index: 2883976 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.7623. Min Act: -0.1700

Data Index: 6822908 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.7469. Min Act: -0.1700

Data Index: 2254355 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.7625. Min Act: -0.1700

Data Index: 987355 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6936. Min Act: -0.1700

Data Index: 6641080 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6600. Min Act: -0.1700

Data Index: 2609749 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6950. Min Act: -0.1700

Data Index: 1543762 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6727. Min Act: -0.1700

Data Index: 3037238 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6466. Min Act: -0.1700

Data Index: 4126345 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6337. Min Act: -0.1700

Data Index: 3956323 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6638. Min Act: -0.1700

Data Index: 8064342 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6171. Min Act: -0.1700

Data Index: 2184424 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6087. Min Act: -0.1700

Data Index: 1192903 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6152. Min Act: -0.1700

Data Index: 3950620 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6101. Min Act: -0.1700

Data Index: 3569215 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6038. Min Act: -0.1700

Data Index: 5521762 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.6208. Min Act: -0.1700

Data Index: 4189345 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.5752. Min Act: -0.1700

Data Index: 3453955 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7667. Min Range: -5.7667

Max Act: 5.5939. Min Act: -0.1700

Data Index: 195829 (Open Web Text)

Max Activating Token Index: 10