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

Dataset: Open Web Text

Neuron 2412 in Layer 4

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: 6.0064. Min Range: -6.0064

Max Act: 6.0064. Min Act: -0.1700

Data Index: 7679529 (Open Web Text)

Max Activating Token Index: 862

Text #1

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.9270. Min Act: -0.1700

Data Index: 1190863 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.9432. Min Act: -0.1700

Data Index: 2226639 (Open Web Text)

Max Activating Token Index: 454

Text #3

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.9404. Min Act: -0.1700

Data Index: 957479 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.8645. Min Act: -0.1700

Data Index: 2460322 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.9073. Min Act: -0.1700

Data Index: 2606878 (Open Web Text)

Max Activating Token Index: 135

Text #6

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.8796. Min Act: -0.1700

Data Index: 4440605 (Open Web Text)

Max Activating Token Index: 868

Text #7

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.8185. Min Act: -0.1700

Data Index: 5323880 (Open Web Text)

Max Activating Token Index: 345

Text #8

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.8297. Min Act: -0.1700

Data Index: 2777154 (Open Web Text)

Max Activating Token Index: 53

Text #9

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7589. Min Act: -0.1700

Data Index: 7439986 (Open Web Text)

Max Activating Token Index: 1013

Text #10

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7653. Min Act: -0.1700

Data Index: 7049394 (Open Web Text)

Max Activating Token Index: 765

Text #11

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7965. Min Act: -0.1700

Data Index: 3038797 (Open Web Text)

Max Activating Token Index: 276

Text #12

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7345. Min Act: -0.1700

Data Index: 1421480 (Open Web Text)

Max Activating Token Index: 1007

Text #13

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7829. Min Act: -0.1700

Data Index: 1296032 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.7272. Min Act: -0.1700

Data Index: 6729693 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.6609. Min Act: -0.1700

Data Index: 6515220 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.6302. Min Act: -0.1700

Data Index: 6940556 (Open Web Text)

Max Activating Token Index: 40

Text #17

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.6481. Min Act: -0.1700

Data Index: 351714 (Open Web Text)

Max Activating Token Index: 314

Text #18

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.6194. Min Act: -0.1700

Data Index: 5938983 (Open Web Text)

Max Activating Token Index: 821

Text #19

Max Range: 6.0064. Min Range: -6.0064

Max Act: 5.5981. Min Act: -0.1700

Data Index: 2808044 (Open Web Text)

Max Activating Token Index: 298