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

Dataset: Open Web Text

Neuron 1348 in Layer 0

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: 2.9578. Min Range: -2.9578

Max Act: 2.9578. Min Act: -0.1700

Data Index: 3800377 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9578. Min Act: -0.1700

Data Index: 6201968 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 1818284 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 8703562 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 8697450 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 8340522 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 8007739 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 7669259 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 774143 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 6583167 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 2534589 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9261. Min Act: -0.1700

Data Index: 5907392 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9259. Min Act: -0.1700

Data Index: 5707756 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 4770176 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 5974347 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 5895980 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 3656346 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9269. Min Act: -0.1700

Data Index: 4375780 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.9160. Min Act: -0.1700

Data Index: 4398534 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9578. Min Range: -2.9578

Max Act: 2.8866. Min Act: -0.1700

Data Index: 139909 (Open Web Text)

Max Activating Token Index: 4