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

Dataset: Open Web Text

Neuron 2459 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: 4.0027. Min Range: -4.0027

Max Act: 4.0027. Min Act: -0.1700

Data Index: 5927109 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.9953. Min Act: -0.1700

Data Index: 3805963 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.9860. Min Act: -0.1700

Data Index: 4216517 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.9521. Min Act: -0.1700

Data Index: 1999999 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.9521. Min Act: -0.1700

Data Index: 5508347 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8955. Min Act: -0.1700

Data Index: 3540052 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8749. Min Act: -0.1700

Data Index: 2390360 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8777. Min Act: -0.1700

Data Index: 8072754 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8852. Min Act: -0.1700

Data Index: 2587243 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8618. Min Act: -0.1700

Data Index: 486092 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8589. Min Act: -0.1700

Data Index: 2418285 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8603. Min Act: -0.1700

Data Index: 7885708 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8468. Min Act: -0.1700

Data Index: 4059348 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8547. Min Act: -0.1700

Data Index: 1553988 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8379. Min Act: -0.1700

Data Index: 4248096 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8296. Min Act: -0.1700

Data Index: 76808 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8473. Min Act: -0.1700

Data Index: 5434004 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8389. Min Act: -0.1700

Data Index: 1882112 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8465. Min Act: -0.1700

Data Index: 5934258 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.0027. Min Range: -4.0027

Max Act: 3.8598. Min Act: -0.1700

Data Index: 6041465 (Open Web Text)

Max Activating Token Index: 3