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

Dataset: Open Web Text

Neuron 2398 in Layer 3

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: 4.6053. Min Range: -4.6053

Max Act: 4.5857. Min Act: -0.1700

Data Index: 7276045 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.6053. Min Act: -0.1700

Data Index: 7735889 (Open Web Text)

Max Activating Token Index: 425

Text #2

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.5493. Min Act: -0.1700

Data Index: 1450150 (Open Web Text)

Max Activating Token Index: 255

Text #3

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.5849. Min Act: -0.1700

Data Index: 5674546 (Open Web Text)

Max Activating Token Index: 451

Text #4

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.5121. Min Act: -0.1700

Data Index: 3718518 (Open Web Text)

Max Activating Token Index: 863

Text #5

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.5131. Min Act: -0.1700

Data Index: 7176172 (Open Web Text)

Max Activating Token Index: 568

Text #6

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.5004. Min Act: -0.1700

Data Index: 1345651 (Open Web Text)

Max Activating Token Index: 48

Text #7

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4670. Min Act: -0.1700

Data Index: 8799626 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4495. Min Act: -0.1700

Data Index: 7781685 (Open Web Text)

Max Activating Token Index: 238

Text #9

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4685. Min Act: -0.1700

Data Index: 8404246 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4818. Min Act: -0.1700

Data Index: 3725676 (Open Web Text)

Max Activating Token Index: 613

Text #11

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4497. Min Act: -0.1700

Data Index: 7636642 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4026. Min Act: -0.1700

Data Index: 3654050 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4014. Min Act: -0.1700

Data Index: 5405874 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.4106. Min Act: -0.1700

Data Index: 6324893 (Open Web Text)

Max Activating Token Index: 195

Text #15

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.3707. Min Act: -0.1700

Data Index: 8038580 (Open Web Text)

Max Activating Token Index: 703

Text #16

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.3981. Min Act: -0.1700

Data Index: 5924940 (Open Web Text)

Max Activating Token Index: 625

Text #17

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.3587. Min Act: -0.1700

Data Index: 3682952 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.3764. Min Act: -0.1700

Data Index: 6247632 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 4.6053. Min Range: -4.6053

Max Act: 4.3656. Min Act: -0.1700

Data Index: 594499 (Open Web Text)

Max Activating Token Index: 159