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

Dataset: Open Web Text

Neuron 873 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: 2.1108. Min Range: -2.1108

Max Act: 2.1108. Min Act: -0.1700

Data Index: 2984638 (Open Web Text)

Max Activating Token Index: 81

Text #1

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0863. Min Act: -0.1700

Data Index: 6700880 (Open Web Text)

Max Activating Token Index: 1019

Text #2

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0862. Min Act: -0.1700

Data Index: 549150 (Open Web Text)

Max Activating Token Index: 782

Text #3

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0812. Min Act: -0.1656

Data Index: 8035772 (Open Web Text)

Max Activating Token Index: 375

Text #4

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0652. Min Act: -0.1700

Data Index: 2532567 (Open Web Text)

Max Activating Token Index: 74

Text #5

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0424. Min Act: -0.1700

Data Index: 1338172 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0346. Min Act: -0.1700

Data Index: 4862746 (Open Web Text)

Max Activating Token Index: 341

Text #7

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0184. Min Act: -0.1700

Data Index: 7791012 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0224. Min Act: -0.1700

Data Index: 6069245 (Open Web Text)

Max Activating Token Index: 289

Text #9

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0091. Min Act: -0.1611

Data Index: 6963654 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0053. Min Act: -0.1618

Data Index: 8421870 (Open Web Text)

Max Activating Token Index: 931

Text #11

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0180. Min Act: -0.1684

Data Index: 8053902 (Open Web Text)

Max Activating Token Index: 908

Text #12

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0093. Min Act: -0.1687

Data Index: 598631 (Open Web Text)

Max Activating Token Index: 188

Text #13

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9887. Min Act: -0.1700

Data Index: 3749960 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9878. Min Act: -0.1696

Data Index: 4419911 (Open Web Text)

Max Activating Token Index: 516

Text #15

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9898. Min Act: -0.1674

Data Index: 8053903 (Open Web Text)

Max Activating Token Index: 877

Text #16

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9885. Min Act: -0.1286

Data Index: 262677 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 2.1108. Min Range: -2.1108

Max Act: 2.0095. Min Act: -0.1700

Data Index: 4522894 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9943. Min Act: -0.1692

Data Index: 4623629 (Open Web Text)

Max Activating Token Index: 475

Text #19

Max Range: 2.1108. Min Range: -2.1108

Max Act: 1.9680. Min Act: -0.1700

Data Index: 1854775 (Open Web Text)

Max Activating Token Index: 565