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

Dataset: Open Web Text

Neuron 2828 in Layer 1

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: 4.3022. Min Range: -4.3022

Max Act: 4.3022. Min Act: -0.1642

Data Index: 8827046 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.3022. Min Range: -4.3022

Max Act: 4.2058. Min Act: -0.1700

Data Index: 8827045 (Open Web Text)

Max Activating Token Index: 757

Text #2

Max Range: 4.3022. Min Range: -4.3022

Max Act: 4.1943. Min Act: -0.1700

Data Index: 3121360 (Open Web Text)

Max Activating Token Index: 173

Text #3

Max Range: 4.3022. Min Range: -4.3022

Max Act: 4.1338. Min Act: -0.1678

Data Index: 8827047 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 4.3022. Min Range: -4.3022

Max Act: 4.0745. Min Act: -0.1700

Data Index: 4243546 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9863. Min Act: -0.1696

Data Index: 7078294 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9567. Min Act: -0.1700

Data Index: 1816191 (Open Web Text)

Max Activating Token Index: 61

Text #7

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9555. Min Act: -0.1700

Data Index: 4909188 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9578. Min Act: -0.1700

Data Index: 8827048 (Open Web Text)

Max Activating Token Index: 221

Text #9

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9239. Min Act: -0.1700

Data Index: 4243547 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9224. Min Act: -0.1700

Data Index: 7078292 (Open Web Text)

Max Activating Token Index: 256

Text #11

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.9017. Min Act: -0.1700

Data Index: 7078293 (Open Web Text)

Max Activating Token Index: 44

Text #12

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.8473. Min Act: -0.1700

Data Index: 4243545 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.8693. Min Act: -0.1700

Data Index: 3525632 (Open Web Text)

Max Activating Token Index: 154

Text #14

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.8692. Min Act: -0.1700

Data Index: 1210068 (Open Web Text)

Max Activating Token Index: 23

Text #15

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.7988. Min Act: -0.1678

Data Index: 5480527 (Open Web Text)

Max Activating Token Index: 85

Text #16

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.7634. Min Act: -0.1700

Data Index: 7078295 (Open Web Text)

Max Activating Token Index: 47

Text #17

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.7836. Min Act: -0.1700

Data Index: 5480528 (Open Web Text)

Max Activating Token Index: 565

Text #18

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.7465. Min Act: -0.1700

Data Index: 8543867 (Open Web Text)

Max Activating Token Index: 58

Text #19

Max Range: 4.3022. Min Range: -4.3022

Max Act: 3.7542. Min Act: -0.1700

Data Index: 7078298 (Open Web Text)

Max Activating Token Index: 61