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

Dataset: Open Web Text

Neuron 2615 in Layer 2

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: 3.5851. Min Range: -3.5851

Max Act: 3.5851. Min Act: -0.1700

Data Index: 3983834 (Open Web Text)

Max Activating Token Index: 859

Text #1

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5479. Min Act: -0.1700

Data Index: 6868675 (Open Web Text)

Max Activating Token Index: 387

Text #2

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5302. Min Act: -0.1700

Data Index: 7942102 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5449. Min Act: -0.1700

Data Index: 5357028 (Open Web Text)

Max Activating Token Index: 186

Text #4

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5238. Min Act: -0.1700

Data Index: 8441116 (Open Web Text)

Max Activating Token Index: 257

Text #5

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5096. Min Act: -0.1700

Data Index: 191566 (Open Web Text)

Max Activating Token Index: 929

Text #6

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5362. Min Act: -0.1700

Data Index: 102846 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5112. Min Act: -0.1700

Data Index: 8242682 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5109. Min Act: -0.1700

Data Index: 2371819 (Open Web Text)

Max Activating Token Index: 1012

Text #9

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4986. Min Act: -0.1700

Data Index: 7250052 (Open Web Text)

Max Activating Token Index: 764

Text #10

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5100. Min Act: -0.1700

Data Index: 2654887 (Open Web Text)

Max Activating Token Index: 629

Text #11

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.5088. Min Act: -0.1700

Data Index: 676927 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4987. Min Act: -0.1700

Data Index: 5302586 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4687. Min Act: -0.1700

Data Index: 8141056 (Open Web Text)

Max Activating Token Index: 365

Text #14

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4916. Min Act: -0.1700

Data Index: 803057 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4907. Min Act: -0.1700

Data Index: 7123021 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4722. Min Act: -0.1700

Data Index: 6636598 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4792. Min Act: -0.1700

Data Index: 2175587 (Open Web Text)

Max Activating Token Index: 842

Text #18

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4623. Min Act: -0.1700

Data Index: 7966551 (Open Web Text)

Max Activating Token Index: 468

Text #19

Max Range: 3.5851. Min Range: -3.5851

Max Act: 3.4388. Min Act: -0.1700

Data Index: 949317 (Open Web Text)

Max Activating Token Index: 624