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

Dataset: Open Web Text

Neuron 1946 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: 3.4286. Min Range: -3.4286

Max Act: 3.4286. Min Act: -0.1700

Data Index: 1939787 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.3550. Min Act: -0.1700

Data Index: 8532189 (Open Web Text)

Max Activating Token Index: 888

Text #2

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.3375. Min Act: -0.1700

Data Index: 3725194 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.3076. Min Act: -0.1700

Data Index: 4887906 (Open Web Text)

Max Activating Token Index: 1021

Text #4

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2915. Min Act: -0.1700

Data Index: 2849575 (Open Web Text)

Max Activating Token Index: 75

Text #5

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.3038. Min Act: -0.1700

Data Index: 4368713 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2902. Min Act: -0.1700

Data Index: 5093509 (Open Web Text)

Max Activating Token Index: 316

Text #7

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2777. Min Act: -0.1700

Data Index: 6352738 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2727. Min Act: -0.1700

Data Index: 184885 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2889. Min Act: -0.1700

Data Index: 7457044 (Open Web Text)

Max Activating Token Index: 145

Text #10

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2911. Min Act: -0.1700

Data Index: 1834220 (Open Web Text)

Max Activating Token Index: 235

Text #11

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2608. Min Act: -0.1700

Data Index: 7531543 (Open Web Text)

Max Activating Token Index: 613

Text #12

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2806. Min Act: -0.1700

Data Index: 7589083 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2862. Min Act: -0.1700

Data Index: 7142420 (Open Web Text)

Max Activating Token Index: 707

Text #14

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2683. Min Act: -0.1700

Data Index: 5761724 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2737. Min Act: -0.1700

Data Index: 6039504 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2518. Min Act: -0.1700

Data Index: 1897018 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2506. Min Act: -0.1700

Data Index: 1037659 (Open Web Text)

Max Activating Token Index: 389

Text #18

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2506. Min Act: -0.1700

Data Index: 4881634 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 3.4286. Min Range: -3.4286

Max Act: 3.2543. Min Act: -0.1700

Data Index: 3580093 (Open Web Text)

Max Activating Token Index: 898