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

Dataset: Open Web Text

Neuron 2796 in Layer 4

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: 3.4873. Min Range: -3.4873

Max Act: 3.4873. Min Act: -0.1700

Data Index: 1998606 (Open Web Text)

Max Activating Token Index: 534

Text #1

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.4817. Min Act: -0.1700

Data Index: 6500980 (Open Web Text)

Max Activating Token Index: 65

Text #2

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.4372. Min Act: -0.1700

Data Index: 4279483 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.4636. Min Act: -0.1700

Data Index: 785647 (Open Web Text)

Max Activating Token Index: 127

Text #4

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.4459. Min Act: -0.1700

Data Index: 3479716 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3855. Min Act: -0.1700

Data Index: 6147230 (Open Web Text)

Max Activating Token Index: 588

Text #6

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3710. Min Act: -0.1700

Data Index: 8668171 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3460. Min Act: -0.1700

Data Index: 4239009 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3379. Min Act: -0.1700

Data Index: 8247752 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3487. Min Act: -0.1700

Data Index: 4636358 (Open Web Text)

Max Activating Token Index: 967

Text #10

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3550. Min Act: -0.1700

Data Index: 6147715 (Open Web Text)

Max Activating Token Index: 431

Text #11

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3316. Min Act: -0.1700

Data Index: 5426857 (Open Web Text)

Max Activating Token Index: 594

Text #12

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3309. Min Act: -0.1700

Data Index: 6557729 (Open Web Text)

Max Activating Token Index: 833

Text #13

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.2980. Min Act: -0.1700

Data Index: 4290335 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3071. Min Act: -0.1700

Data Index: 2542125 (Open Web Text)

Max Activating Token Index: 546

Text #15

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1474847 (Open Web Text)

Max Activating Token Index: 826

Text #16

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.2835. Min Act: -0.1700

Data Index: 148445 (Open Web Text)

Max Activating Token Index: 642

Text #17

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.2852. Min Act: -0.1700

Data Index: 810950 (Open Web Text)

Max Activating Token Index: 813

Text #18

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.2770. Min Act: -0.1700

Data Index: 3953634 (Open Web Text)

Max Activating Token Index: 1011

Text #19

Max Range: 3.4873. Min Range: -3.4873

Max Act: 3.2765. Min Act: -0.1700

Data Index: 8287313 (Open Web Text)

Max Activating Token Index: 563