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

Dataset: Open Web Text

Neuron 500 in Layer 4

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: 3.6994. Min Range: -3.6994

Max Act: 3.6994. Min Act: -0.1700

Data Index: 6626325 (Open Web Text)

Max Activating Token Index: 980

Text #1

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.6775. Min Act: -0.1700

Data Index: 5388665 (Open Web Text)

Max Activating Token Index: 973

Text #2

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.6658. Min Act: -0.1700

Data Index: 5756189 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.6208. Min Act: -0.1700

Data Index: 3365979 (Open Web Text)

Max Activating Token Index: 937

Text #4

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5878. Min Act: -0.1700

Data Index: 994863 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5812. Min Act: -0.1700

Data Index: 5985292 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.5211. Min Act: -0.1700

Data Index: 2263756 (Open Web Text)

Max Activating Token Index: 881

Text #7

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4831. Min Act: -0.1700

Data Index: 3457507 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4973. Min Act: -0.1700

Data Index: 5626092 (Open Web Text)

Max Activating Token Index: 751

Text #9

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4522. Min Act: -0.1700

Data Index: 6647444 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3994. Min Act: -0.1700

Data Index: 3862624 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3828. Min Act: -0.1700

Data Index: 5052256 (Open Web Text)

Max Activating Token Index: 529

Text #12

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3496. Min Act: -0.1700

Data Index: 4673292 (Open Web Text)

Max Activating Token Index: 651

Text #13

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3828. Min Act: -0.1700

Data Index: 8716670 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3700. Min Act: -0.1700

Data Index: 5626106 (Open Web Text)

Max Activating Token Index: 703

Text #15

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.4043. Min Act: -0.1700

Data Index: 5807110 (Open Web Text)

Max Activating Token Index: 927

Text #16

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3510. Min Act: -0.1700

Data Index: 1975908 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3575. Min Act: -0.1700

Data Index: 7193179 (Open Web Text)

Max Activating Token Index: 277

Text #18

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3246. Min Act: -0.1700

Data Index: 835899 (Open Web Text)

Max Activating Token Index: 737

Text #19

Max Range: 3.6994. Min Range: -3.6994

Max Act: 3.3219. Min Act: -0.1700

Data Index: 600090 (Open Web Text)

Max Activating Token Index: 555