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

Dataset: Open Web Text

Neuron 2160 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: 5.4700. Min Range: -5.4700

Max Act: 5.4700. Min Act: -0.1700

Data Index: 5084932 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4466. Min Act: -0.1700

Data Index: 1169447 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4416. Min Act: -0.1700

Data Index: 913419 (Open Web Text)

Max Activating Token Index: 15

Text #3

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4070. Min Act: -0.1700

Data Index: 4688918 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4159. Min Act: -0.1700

Data Index: 4354692 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3946. Min Act: -0.1700

Data Index: 7236336 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4153. Min Act: -0.1700

Data Index: 4085503 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4166. Min Act: -0.1700

Data Index: 2078724 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.4057. Min Act: -0.1700

Data Index: 6369501 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3559. Min Act: -0.1700

Data Index: 4310857 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3671. Min Act: -0.1700

Data Index: 1923944 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3614. Min Act: -0.1700

Data Index: 8779603 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3715. Min Act: -0.1700

Data Index: 7208775 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3471. Min Act: -0.1700

Data Index: 5631720 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3430. Min Act: -0.1700

Data Index: 5122350 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3359. Min Act: -0.1700

Data Index: 2287338 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3354. Min Act: -0.1700

Data Index: 3339324 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3548. Min Act: -0.1700

Data Index: 4391208 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3518. Min Act: -0.1700

Data Index: 7853389 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.4700. Min Range: -5.4700

Max Act: 5.3634. Min Act: -0.1700

Data Index: 4665633 (Open Web Text)

Max Activating Token Index: 8