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

Dataset: Open Web Text

Neuron 2970 in Layer 1

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: 1.9729. Min Range: -1.9729

Max Act: 1.9729. Min Act: -0.1700

Data Index: 7023515 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9320. Min Act: -0.1700

Data Index: 2841531 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9242. Min Act: -0.1700

Data Index: 8471248 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9219. Min Act: -0.1700

Data Index: 4309923 (Open Web Text)

Max Activating Token Index: 409

Text #4

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.9123. Min Act: -0.1700

Data Index: 6126629 (Open Web Text)

Max Activating Token Index: 735

Text #5

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8987. Min Act: -0.1700

Data Index: 1920778 (Open Web Text)

Max Activating Token Index: 478

Text #6

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8984. Min Act: -0.1700

Data Index: 2166748 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8991. Min Act: -0.1700

Data Index: 4754807 (Open Web Text)

Max Activating Token Index: 583

Text #8

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8859. Min Act: -0.1700

Data Index: 2023474 (Open Web Text)

Max Activating Token Index: 627

Text #9

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8898. Min Act: -0.1699

Data Index: 2475947 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8901. Min Act: -0.1699

Data Index: 2761726 (Open Web Text)

Max Activating Token Index: 121

Text #11

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8765. Min Act: -0.1700

Data Index: 7440841 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8783. Min Act: -0.1700

Data Index: 2988982 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8821. Min Act: -0.1700

Data Index: 1658690 (Open Web Text)

Max Activating Token Index: 610

Text #14

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8832. Min Act: -0.1700

Data Index: 1660789 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8726. Min Act: -0.1700

Data Index: 4761172 (Open Web Text)

Max Activating Token Index: 71

Text #16

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8751. Min Act: -0.1700

Data Index: 4503337 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8729. Min Act: -0.1700

Data Index: 7542605 (Open Web Text)

Max Activating Token Index: 774

Text #18

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8715. Min Act: -0.1700

Data Index: 1946827 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 1.9729. Min Range: -1.9729

Max Act: 1.8721. Min Act: -0.1700

Data Index: 2506374 (Open Web Text)

Max Activating Token Index: 533