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

Dataset: Open Web Text

Neuron 1076 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: 5.7374. Min Range: -5.7374

Max Act: 5.7327. Min Act: -0.1700

Data Index: 6755100 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.7283. Min Act: -0.1700

Data Index: 6533258 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.7374. Min Act: -0.1700

Data Index: 3882873 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6825. Min Act: -0.1700

Data Index: 8730489 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.7040. Min Act: -0.1700

Data Index: 3575406 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6630. Min Act: -0.1700

Data Index: 3093088 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6746. Min Act: -0.1700

Data Index: 3899364 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6889. Min Act: -0.1700

Data Index: 756172 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6702. Min Act: -0.1700

Data Index: 7861070 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6691. Min Act: -0.1700

Data Index: 694072 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6339. Min Act: -0.1700

Data Index: 7912352 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6524. Min Act: -0.1700

Data Index: 2497368 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6349. Min Act: -0.1700

Data Index: 3480938 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6348. Min Act: -0.1700

Data Index: 5387301 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6384. Min Act: -0.1700

Data Index: 8180236 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6349. Min Act: -0.1700

Data Index: 5756605 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6349. Min Act: -0.1700

Data Index: 5872597 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6384. Min Act: -0.1700

Data Index: 1010616 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.6341. Min Act: -0.1700

Data Index: 7761681 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.7374. Min Range: -5.7374

Max Act: 5.5932. Min Act: -0.1700

Data Index: 1367533 (Open Web Text)

Max Activating Token Index: 3