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

Dataset: Open Web Text

Neuron 2306 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: 1.2941. Min Range: -1.2941

Max Act: 1.2857. Min Act: -0.1700

Data Index: 2121631 (Open Web Text)

Max Activating Token Index: 521

Text #1

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2806. Min Act: -0.1700

Data Index: 8098852 (Open Web Text)

Max Activating Token Index: 548

Text #2

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2816. Min Act: -0.1700

Data Index: 8112522 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2941. Min Act: -0.1700

Data Index: 1883905 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2817. Min Act: -0.1700

Data Index: 2732506 (Open Web Text)

Max Activating Token Index: 149

Text #5

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2752. Min Act: -0.1700

Data Index: 5544111 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2792. Min Act: -0.1700

Data Index: 5362415 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2840. Min Act: -0.1700

Data Index: 4182358 (Open Web Text)

Max Activating Token Index: 521

Text #8

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2630. Min Act: -0.1700

Data Index: 1652080 (Open Web Text)

Max Activating Token Index: 128

Text #9

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2699. Min Act: -0.1700

Data Index: 5601968 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2737. Min Act: -0.1700

Data Index: 4725929 (Open Web Text)

Max Activating Token Index: 139

Text #11

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2639. Min Act: -0.1700

Data Index: 4605817 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2758. Min Act: -0.1700

Data Index: 1001840 (Open Web Text)

Max Activating Token Index: 525

Text #13

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2745. Min Act: -0.1700

Data Index: 4251346 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2696. Min Act: -0.1700

Data Index: 910950 (Open Web Text)

Max Activating Token Index: 556

Text #15

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2651. Min Act: -0.1700

Data Index: 3888488 (Open Web Text)

Max Activating Token Index: 544

Text #16

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2725. Min Act: -0.1700

Data Index: 3827729 (Open Web Text)

Max Activating Token Index: 128

Text #17

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2629. Min Act: -0.1700

Data Index: 3136427 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2790. Min Act: -0.1700

Data Index: 2992548 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 1.2941. Min Range: -1.2941

Max Act: 1.2607. Min Act: -0.1700

Data Index: 2615538 (Open Web Text)

Max Activating Token Index: 169