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

Dataset: Open Web Text

Neuron 2504 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: 4.4727. Min Range: -4.4727

Max Act: 4.4727. Min Act: -0.1700

Data Index: 144171 (Open Web Text)

Max Activating Token Index: 69

Text #1

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.4368. Min Act: -0.1700

Data Index: 6154737 (Open Web Text)

Max Activating Token Index: 113

Text #2

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.4317. Min Act: -0.1700

Data Index: 3202628 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3624. Min Act: -0.1700

Data Index: 8235067 (Open Web Text)

Max Activating Token Index: 862

Text #4

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3478. Min Act: -0.1700

Data Index: 7210608 (Open Web Text)

Max Activating Token Index: 574

Text #5

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3604. Min Act: -0.1700

Data Index: 8629942 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3177. Min Act: -0.1700

Data Index: 8197304 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3108. Min Act: -0.1700

Data Index: 2748682 (Open Web Text)

Max Activating Token Index: 122

Text #8

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3160. Min Act: -0.1700

Data Index: 5221136 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3282. Min Act: -0.1700

Data Index: 344953 (Open Web Text)

Max Activating Token Index: 500

Text #10

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3008. Min Act: -0.1700

Data Index: 3008889 (Open Web Text)

Max Activating Token Index: 466

Text #11

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3044. Min Act: -0.1700

Data Index: 8186250 (Open Web Text)

Max Activating Token Index: 492

Text #12

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.3028. Min Act: -0.1700

Data Index: 4979864 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2909. Min Act: -0.1700

Data Index: 4663487 (Open Web Text)

Max Activating Token Index: 126

Text #14

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2480. Min Act: -0.1700

Data Index: 6443719 (Open Web Text)

Max Activating Token Index: 470

Text #15

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2311. Min Act: -0.1700

Data Index: 4601487 (Open Web Text)

Max Activating Token Index: 416

Text #16

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2288. Min Act: -0.1700

Data Index: 2883427 (Open Web Text)

Max Activating Token Index: 105

Text #17

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2346. Min Act: -0.1700

Data Index: 6610268 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2284. Min Act: -0.1700

Data Index: 20808 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 4.4727. Min Range: -4.4727

Max Act: 4.2202. Min Act: -0.1700

Data Index: 5228553 (Open Web Text)

Max Activating Token Index: 156