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

Dataset: Open Web Text

Neuron 1838 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: 3.3963. Min Range: -3.3963

Max Act: 3.3963. Min Act: -0.1700

Data Index: 8482217 (Open Web Text)

Max Activating Token Index: 334

Text #1

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3635. Min Act: -0.1700

Data Index: 6090128 (Open Web Text)

Max Activating Token Index: 681

Text #2

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3495. Min Act: -0.1700

Data Index: 8211595 (Open Web Text)

Max Activating Token Index: 112

Text #3

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3302. Min Act: -0.1700

Data Index: 8422867 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3398. Min Act: -0.1700

Data Index: 2880825 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3095. Min Act: -0.1700

Data Index: 6783700 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2965. Min Act: -0.1700

Data Index: 8489796 (Open Web Text)

Max Activating Token Index: 261

Text #7

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.3033. Min Act: -0.1700

Data Index: 8697243 (Open Web Text)

Max Activating Token Index: 582

Text #8

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2525. Min Act: -0.1700

Data Index: 7517549 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2456. Min Act: -0.1700

Data Index: 75041 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2355. Min Act: -0.1700

Data Index: 2388570 (Open Web Text)

Max Activating Token Index: 556

Text #11

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2505. Min Act: -0.1700

Data Index: 5874243 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2364. Min Act: -0.1700

Data Index: 2227854 (Open Web Text)

Max Activating Token Index: 176

Text #13

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2357. Min Act: -0.1700

Data Index: 6354819 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2434. Min Act: -0.1700

Data Index: 1403877 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2286. Min Act: -0.1700

Data Index: 4462076 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2484. Min Act: -0.1700

Data Index: 4015504 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2503. Min Act: -0.1700

Data Index: 7238794 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2240. Min Act: -0.1700

Data Index: 3981388 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 3.3963. Min Range: -3.3963

Max Act: 3.2257. Min Act: -0.1700

Data Index: 7438001 (Open Web Text)

Max Activating Token Index: 844