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

Dataset: Open Web Text

Neuron 1657 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: 2.8471. Min Range: -2.8471

Max Act: 2.8471. Min Act: -0.1700

Data Index: 8554845 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.8471. Min Act: -0.1700

Data Index: 5105166 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.8150. Min Act: -0.1700

Data Index: 3773397 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.8045. Min Act: -0.1700

Data Index: 7643128 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7963. Min Act: -0.1700

Data Index: 4158127 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7976. Min Act: -0.1700

Data Index: 2376605 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7713. Min Act: -0.1700

Data Index: 3411505 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7763. Min Act: -0.1700

Data Index: 746112 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7636. Min Act: -0.1700

Data Index: 4684368 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7495. Min Act: -0.1700

Data Index: 6004806 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7444. Min Act: -0.1700

Data Index: 6193290 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7438. Min Act: -0.1700

Data Index: 6758501 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7228. Min Act: -0.1700

Data Index: 6768032 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7255. Min Act: -0.1700

Data Index: 7787906 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7334. Min Act: -0.1700

Data Index: 2640647 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7253. Min Act: -0.1700

Data Index: 5682580 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7271. Min Act: -0.1700

Data Index: 2308726 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7312. Min Act: -0.1700

Data Index: 3750359 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7345. Min Act: -0.1700

Data Index: 2153777 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 2.8471. Min Range: -2.8471

Max Act: 2.7349. Min Act: -0.1700

Data Index: 8375594 (Open Web Text)

Max Activating Token Index: 7