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

Dataset: Open Web Text

Neuron 733 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: 4.9662. Min Range: -4.9662

Max Act: 4.9662. Min Act: -0.1700

Data Index: 1278464 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.9365. Min Act: -0.1700

Data Index: 3956696 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8535. Min Act: -0.1700

Data Index: 486008 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8535. Min Act: -0.1700

Data Index: 4174007 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8535. Min Act: -0.1700

Data Index: 7081206 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8747. Min Act: -0.1700

Data Index: 8481642 (Open Web Text)

Max Activating Token Index: 522

Text #6

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8461. Min Act: -0.1700

Data Index: 2846036 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8315. Min Act: -0.1700

Data Index: 4850 (Open Web Text)

Max Activating Token Index: 811

Text #8

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8206. Min Act: -0.1700

Data Index: 3059253 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8409. Min Act: -0.1700

Data Index: 2957315 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8314. Min Act: -0.1700

Data Index: 246420 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8251. Min Act: -0.1700

Data Index: 6107246 (Open Web Text)

Max Activating Token Index: 383

Text #12

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8232. Min Act: -0.1700

Data Index: 826731 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8507. Min Act: -0.1700

Data Index: 8104415 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8374. Min Act: -0.1700

Data Index: 1791581 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8162. Min Act: -0.1700

Data Index: 6704316 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.7899. Min Act: -0.1700

Data Index: 24421 (Open Web Text)

Max Activating Token Index: 723

Text #17

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8049. Min Act: -0.1700

Data Index: 6751253 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8156. Min Act: -0.1700

Data Index: 408662 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.9662. Min Range: -4.9662

Max Act: 4.8203. Min Act: -0.1700

Data Index: 4778104 (Open Web Text)

Max Activating Token Index: 6