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

Dataset: Open Web Text

Neuron 787 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: 3.6001. Min Range: -3.6001

Max Act: 3.6001. Min Act: -0.1700

Data Index: 7415334 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5772. Min Act: -0.1700

Data Index: 6039154 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5817. Min Act: -0.1700

Data Index: 3856147 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5833. Min Act: -0.1700

Data Index: 5645460 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5683. Min Act: -0.1700

Data Index: 5641359 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5765. Min Act: -0.1700

Data Index: 8124598 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5641. Min Act: -0.1700

Data Index: 8750575 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5402. Min Act: -0.1700

Data Index: 4698409 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5504. Min Act: -0.1700

Data Index: 6883852 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5416. Min Act: -0.1700

Data Index: 1766634 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5447. Min Act: -0.1700

Data Index: 2131297 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5440. Min Act: -0.1700

Data Index: 8612298 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5376. Min Act: -0.1700

Data Index: 358040 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5314. Min Act: -0.1700

Data Index: 7804321 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5273. Min Act: -0.1700

Data Index: 6986689 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5319. Min Act: -0.1700

Data Index: 8574418 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5310. Min Act: -0.1700

Data Index: 6867134 (Open Web Text)

Max Activating Token Index: 736

Text #17

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5318. Min Act: -0.1700

Data Index: 5790789 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5320. Min Act: -0.1700

Data Index: 5859478 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.6001. Min Range: -3.6001

Max Act: 3.5337. Min Act: -0.1700

Data Index: 4178148 (Open Web Text)

Max Activating Token Index: 5