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

Dataset: Open Web Text

Neuron 1834 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: 3.1965. Min Range: -3.1965

Max Act: 3.1936. Min Act: -0.1700

Data Index: 5744383 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1965. Min Act: -0.1700

Data Index: 7565525 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1558. Min Act: -0.1700

Data Index: 5054248 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1483. Min Act: -0.1700

Data Index: 3478509 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1456. Min Act: -0.1700

Data Index: 3339932 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1389. Min Act: -0.1700

Data Index: 1029634 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1101. Min Act: -0.1700

Data Index: 188432 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1133. Min Act: -0.1700

Data Index: 6825209 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.1066. Min Act: -0.1700

Data Index: 4057588 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1784094 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0765. Min Act: -0.1700

Data Index: 1587910 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0518. Min Act: -0.1700

Data Index: 3259358 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0571. Min Act: -0.1700

Data Index: 663500 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0412. Min Act: -0.1700

Data Index: 6447671 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0419. Min Act: -0.1700

Data Index: 6197461 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0394. Min Act: -0.1700

Data Index: 2830911 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0480. Min Act: -0.1700

Data Index: 1473802 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0465. Min Act: -0.1700

Data Index: 73326 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0368. Min Act: -0.1700

Data Index: 4952980 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1965. Min Range: -3.1965

Max Act: 3.0338. Min Act: -0.1700

Data Index: 8679166 (Open Web Text)

Max Activating Token Index: 9