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

Dataset: Open Web Text

Neuron 1457 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: 5.4825. Min Range: -5.4825

Max Act: 5.4825. Min Act: -0.1700

Data Index: 2248848 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.4076. Min Act: -0.1700

Data Index: 4753799 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.3696. Min Act: -0.1700

Data Index: 4351067 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.3479. Min Act: -0.1700

Data Index: 2815652 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.3311. Min Act: -0.1700

Data Index: 6374609 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.3059. Min Act: -0.1700

Data Index: 5190709 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2795. Min Act: -0.1700

Data Index: 2451198 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2630. Min Act: -0.1700

Data Index: 819093 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2656. Min Act: -0.1700

Data Index: 5847943 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2622. Min Act: -0.1700

Data Index: 8542791 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2751. Min Act: -0.1700

Data Index: 1078463 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2430. Min Act: -0.1700

Data Index: 7029991 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2222. Min Act: -0.1700

Data Index: 8064292 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2461. Min Act: -0.1700

Data Index: 8449265 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2226. Min Act: -0.1700

Data Index: 1252919 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2453. Min Act: -0.1700

Data Index: 879486 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2084. Min Act: -0.1700

Data Index: 3261091 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2008. Min Act: -0.1700

Data Index: 2296913 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.1994. Min Act: -0.1700

Data Index: 7082163 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.4825. Min Range: -5.4825

Max Act: 5.2057. Min Act: -0.1700

Data Index: 7240327 (Open Web Text)

Max Activating Token Index: 7