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

Dataset: Open Web Text

Neuron 2124 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: 2.7211. Min Range: -2.7211

Max Act: 2.7124. Min Act: -0.1700

Data Index: 2876350 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.7211. Min Act: -0.1700

Data Index: 2240605 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6988. Min Act: -0.1700

Data Index: 3375374 (Open Web Text)

Max Activating Token Index: 61

Text #3

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.7087. Min Act: -0.1700

Data Index: 5360049 (Open Web Text)

Max Activating Token Index: 25

Text #4

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6862. Min Act: -0.1700

Data Index: 2276970 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6638. Min Act: -0.1700

Data Index: 5907291 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6515. Min Act: -0.1700

Data Index: 7269669 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6566. Min Act: -0.1700

Data Index: 7998663 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6548. Min Act: -0.1700

Data Index: 1394071 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6402. Min Act: -0.1700

Data Index: 469279 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6413. Min Act: -0.1700

Data Index: 2420499 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6462. Min Act: -0.1700

Data Index: 4129628 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6389. Min Act: -0.1700

Data Index: 8001966 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6209. Min Act: -0.1700

Data Index: 4301617 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6201. Min Act: -0.1700

Data Index: 1093178 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6160. Min Act: -0.1700

Data Index: 2226585 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6201. Min Act: -0.1700

Data Index: 5778230 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6228. Min Act: -0.1700

Data Index: 3731786 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6190. Min Act: -0.1700

Data Index: 506843 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.7211. Min Range: -2.7211

Max Act: 2.6192. Min Act: -0.1700

Data Index: 3469216 (Open Web Text)

Max Activating Token Index: 78