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

Dataset: Open Web Text

Neuron 2549 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: 6.4045. Min Range: -6.4045

Max Act: 6.3786. Min Act: -0.1700

Data Index: 6541702 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.4045. Min Act: -0.1700

Data Index: 1813252 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3740. Min Act: -0.1700

Data Index: 2190444 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3713. Min Act: -0.1700

Data Index: 6332101 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3572. Min Act: -0.1700

Data Index: 519010 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3573. Min Act: -0.1700

Data Index: 7421994 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3161. Min Act: -0.1700

Data Index: 7650919 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3379. Min Act: -0.1700

Data Index: 8715860 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3262. Min Act: -0.1700

Data Index: 2529547 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3259. Min Act: -0.1700

Data Index: 4031429 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.3013. Min Act: -0.1700

Data Index: 4097279 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2960. Min Act: -0.1700

Data Index: 6977196 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2843. Min Act: -0.1700

Data Index: 8162300 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2680. Min Act: -0.1700

Data Index: 5968073 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2207. Min Act: -0.1700

Data Index: 6112939 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2328. Min Act: -0.1700

Data Index: 3501030 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2142. Min Act: -0.1700

Data Index: 1218690 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2353. Min Act: -0.1700

Data Index: 6175457 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2488. Min Act: -0.1700

Data Index: 3528833 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 6.4045. Min Range: -6.4045

Max Act: 6.2475. Min Act: -0.1700

Data Index: 3619745 (Open Web Text)

Max Activating Token Index: 4