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

Dataset: Open Web Text

Neuron 1158 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: 3.6374. Min Range: -3.6374

Max Act: 3.6374. Min Act: -0.1700

Data Index: 7503755 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6196. Min Act: -0.1700

Data Index: 690929 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6033. Min Act: -0.1700

Data Index: 2263819 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5814. Min Act: -0.1700

Data Index: 4012611 (Open Web Text)

Max Activating Token Index: 97

Text #4

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6064. Min Act: -0.1700

Data Index: 37974 (Open Web Text)

Max Activating Token Index: 604

Text #5

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.6214. Min Act: -0.1700

Data Index: 2263823 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5849. Min Act: -0.1700

Data Index: 6271688 (Open Web Text)

Max Activating Token Index: 43

Text #7

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5738. Min Act: -0.1700

Data Index: 1953308 (Open Web Text)

Max Activating Token Index: 572

Text #8

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5516. Min Act: -0.1700

Data Index: 8345202 (Open Web Text)

Max Activating Token Index: 463

Text #9

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5258. Min Act: -0.1700

Data Index: 6389617 (Open Web Text)

Max Activating Token Index: 82

Text #10

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5360. Min Act: -0.1700

Data Index: 652757 (Open Web Text)

Max Activating Token Index: 329

Text #11

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5287. Min Act: -0.1700

Data Index: 7503751 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4972. Min Act: -0.1700

Data Index: 941896 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4988. Min Act: -0.1700

Data Index: 1734810 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4868. Min Act: -0.1700

Data Index: 1774869 (Open Web Text)

Max Activating Token Index: 496

Text #15

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5211. Min Act: -0.1700

Data Index: 7314689 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5073. Min Act: -0.1700

Data Index: 7416885 (Open Web Text)

Max Activating Token Index: 585

Text #17

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4949. Min Act: -0.1700

Data Index: 37975 (Open Web Text)

Max Activating Token Index: 223

Text #18

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.5161. Min Act: -0.1700

Data Index: 5215316 (Open Web Text)

Max Activating Token Index: 473

Text #19

Max Range: 3.6374. Min Range: -3.6374

Max Act: 3.4991. Min Act: -0.1700

Data Index: 4462603 (Open Web Text)

Max Activating Token Index: 104