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

Dataset: Open Web Text

Neuron 930 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: 3.6515. Min Range: -3.6515

Max Act: 3.6515. Min Act: -0.1700

Data Index: 4952737 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.5519. Min Act: -0.1700

Data Index: 4131111 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.5220. Min Act: -0.1700

Data Index: 502940 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4810. Min Act: -0.1700

Data Index: 8532504 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4614. Min Act: -0.1700

Data Index: 5751149 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4571. Min Act: -0.1700

Data Index: 3608619 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4602. Min Act: -0.1700

Data Index: 3727191 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4587. Min Act: -0.1700

Data Index: 8777740 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4301. Min Act: -0.1700

Data Index: 5065345 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4249. Min Act: -0.1700

Data Index: 6464353 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4508. Min Act: -0.1700

Data Index: 2030302 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4276. Min Act: -0.1700

Data Index: 5000837 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4377. Min Act: -0.1700

Data Index: 4489648 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4192. Min Act: -0.1700

Data Index: 6658914 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4189. Min Act: -0.1700

Data Index: 7696830 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4104. Min Act: -0.1700

Data Index: 5133473 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4097. Min Act: -0.1700

Data Index: 1463652 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4072. Min Act: -0.1700

Data Index: 2782331 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4098. Min Act: -0.1700

Data Index: 553445 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.6515. Min Range: -3.6515

Max Act: 3.4069. Min Act: -0.1700

Data Index: 1687754 (Open Web Text)

Max Activating Token Index: 4