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

Dataset: Open Web Text

Neuron 588 in Layer 5

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: 3.4007. Min Range: -3.4007

Max Act: 3.4007. Min Act: -0.1700

Data Index: 4440936 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.3004. Min Act: -0.1700

Data Index: 2983921 (Open Web Text)

Max Activating Token Index: 635

Text #2

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2996. Min Act: -0.1700

Data Index: 6281064 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2861. Min Act: -0.1700

Data Index: 5804952 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2880. Min Act: -0.1700

Data Index: 4772395 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2908. Min Act: -0.1700

Data Index: 6083685 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2902. Min Act: -0.1700

Data Index: 979480 (Open Web Text)

Max Activating Token Index: 515

Text #7

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2850. Min Act: -0.1700

Data Index: 110393 (Open Web Text)

Max Activating Token Index: 625

Text #8

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2782. Min Act: -0.1700

Data Index: 7020003 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2786. Min Act: -0.1700

Data Index: 370800 (Open Web Text)

Max Activating Token Index: 87

Text #10

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2820. Min Act: -0.1700

Data Index: 2970717 (Open Web Text)

Max Activating Token Index: 547

Text #11

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2949. Min Act: -0.1700

Data Index: 3230048 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2547. Min Act: -0.1700

Data Index: 1268271 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2622. Min Act: -0.1700

Data Index: 1772859 (Open Web Text)

Max Activating Token Index: 943

Text #14

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2639. Min Act: -0.1700

Data Index: 870649 (Open Web Text)

Max Activating Token Index: 877

Text #15

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2702. Min Act: -0.1700

Data Index: 6083141 (Open Web Text)

Max Activating Token Index: 753

Text #16

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2753. Min Act: -0.1700

Data Index: 7295639 (Open Web Text)

Max Activating Token Index: 233

Text #17

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2729. Min Act: -0.1700

Data Index: 4510754 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2682. Min Act: -0.1700

Data Index: 2723089 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 3.4007. Min Range: -3.4007

Max Act: 3.2803. Min Act: -0.1700

Data Index: 469531 (Open Web Text)

Max Activating Token Index: 1011