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

Dataset: Open Web Text

Neuron 2207 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: 2.6205. Min Range: -2.6205

Max Act: 2.6205. Min Act: -0.1700

Data Index: 947761 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5793. Min Act: -0.1700

Data Index: 6583741 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5599. Min Act: -0.1700

Data Index: 4130546 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5578. Min Act: -0.1700

Data Index: 4381842 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5644. Min Act: -0.1700

Data Index: 2241744 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5499. Min Act: -0.1700

Data Index: 7810530 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5493. Min Act: -0.1700

Data Index: 3997726 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1012513 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5471. Min Act: -0.1700

Data Index: 7898199 (Open Web Text)

Max Activating Token Index: 17

Text #9

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5495. Min Act: -0.1700

Data Index: 8803232 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5405. Min Act: -0.1700

Data Index: 4686138 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5429. Min Act: -0.1700

Data Index: 2524227 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5473. Min Act: -0.1700

Data Index: 1484384 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5458. Min Act: -0.1700

Data Index: 1788606 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5268. Min Act: -0.1700

Data Index: 5960645 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5154. Min Act: -0.1700

Data Index: 5125811 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5344. Min Act: -0.1700

Data Index: 4985905 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5145. Min Act: -0.1700

Data Index: 1678717 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5226. Min Act: -0.1700

Data Index: 2071647 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.6205. Min Range: -2.6205

Max Act: 2.5235. Min Act: -0.1700

Data Index: 1629655 (Open Web Text)

Max Activating Token Index: 16