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

Dataset: Open Web Text

Neuron 947 in Layer 6

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: 3.5512. Min Range: -3.5512

Max Act: 3.5512. Min Act: -0.1700

Data Index: 1062973 (Open Web Text)

Max Activating Token Index: 769

Text #1

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.5113. Min Act: -0.1700

Data Index: 7972269 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.5233. Min Act: -0.1700

Data Index: 1505933 (Open Web Text)

Max Activating Token Index: 251

Text #3

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.5009. Min Act: -0.1700

Data Index: 4103662 (Open Web Text)

Max Activating Token Index: 123

Text #4

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4730. Min Act: -0.1700

Data Index: 1288752 (Open Web Text)

Max Activating Token Index: 163

Text #5

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4508. Min Act: -0.1700

Data Index: 8797803 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4333. Min Act: -0.1700

Data Index: 7950141 (Open Web Text)

Max Activating Token Index: 460

Text #7

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4330. Min Act: -0.1700

Data Index: 5657159 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4289. Min Act: -0.1700

Data Index: 1009056 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4368. Min Act: -0.1700

Data Index: 1545372 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4382. Min Act: -0.1700

Data Index: 2183488 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4202. Min Act: -0.1700

Data Index: 3703235 (Open Web Text)

Max Activating Token Index: 756

Text #12

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4409. Min Act: -0.1700

Data Index: 2341326 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4050. Min Act: -0.1700

Data Index: 4827603 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4220. Min Act: -0.1700

Data Index: 3113731 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4013. Min Act: -0.1700

Data Index: 2929728 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4210. Min Act: -0.1700

Data Index: 7826104 (Open Web Text)

Max Activating Token Index: 799

Text #17

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4109. Min Act: -0.1700

Data Index: 4543745 (Open Web Text)

Max Activating Token Index: 242

Text #18

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.4110. Min Act: -0.1700

Data Index: 4515516 (Open Web Text)

Max Activating Token Index: 668

Text #19

Max Range: 3.5512. Min Range: -3.5512

Max Act: 3.3906. Min Act: -0.1700

Data Index: 3946645 (Open Web Text)

Max Activating Token Index: 54