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

Dataset: Open Web Text

Neuron 1986 in Layer 3

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: 5.6333. Min Range: -5.6333

Max Act: 5.6333. Min Act: -0.1700

Data Index: 6715908 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.5763. Min Act: -0.1700

Data Index: 1480635 (Open Web Text)

Max Activating Token Index: 33

Text #2

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.5378. Min Act: -0.1700

Data Index: 1870588 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4922. Min Act: -0.1700

Data Index: 1026970 (Open Web Text)

Max Activating Token Index: 462

Text #4

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.5172. Min Act: -0.1700

Data Index: 1031333 (Open Web Text)

Max Activating Token Index: 730

Text #5

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4771. Min Act: -0.1700

Data Index: 6203406 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4605. Min Act: -0.1700

Data Index: 1619827 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4547. Min Act: -0.1700

Data Index: 8150845 (Open Web Text)

Max Activating Token Index: 91

Text #8

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3808. Min Act: -0.1700

Data Index: 4900074 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4409. Min Act: -0.1700

Data Index: 3704947 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4000. Min Act: -0.1700

Data Index: 6750153 (Open Web Text)

Max Activating Token Index: 457

Text #11

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.4032. Min Act: -0.1700

Data Index: 1097951 (Open Web Text)

Max Activating Token Index: 256

Text #12

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3401. Min Act: -0.1700

Data Index: 3164445 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3511. Min Act: -0.1700

Data Index: 7538167 (Open Web Text)

Max Activating Token Index: 65

Text #14

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3273. Min Act: -0.1700

Data Index: 6716875 (Open Web Text)

Max Activating Token Index: 120

Text #15

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3278. Min Act: -0.1700

Data Index: 58480 (Open Web Text)

Max Activating Token Index: 533

Text #16

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3338. Min Act: -0.1700

Data Index: 1464142 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.2904. Min Act: -0.1700

Data Index: 2646970 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3231. Min Act: -0.1700

Data Index: 3224397 (Open Web Text)

Max Activating Token Index: 56

Text #19

Max Range: 5.6333. Min Range: -5.6333

Max Act: 5.3057. Min Act: -0.1700

Data Index: 3587585 (Open Web Text)

Max Activating Token Index: 18