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

Dataset: Open Web Text

Neuron 589 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: 3.9168. Min Range: -3.9168

Max Act: 3.9168. Min Act: -0.1700

Data Index: 7845103 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8365. Min Act: -0.1700

Data Index: 2478029 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8174. Min Act: -0.1700

Data Index: 2284938 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8151. Min Act: -0.1700

Data Index: 8079915 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8300. Min Act: -0.1700

Data Index: 4691785 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8188. Min Act: -0.1700

Data Index: 5389242 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7877. Min Act: -0.1700

Data Index: 3827606 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8061. Min Act: -0.1700

Data Index: 2065230 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7784. Min Act: -0.1700

Data Index: 3165852 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7773. Min Act: -0.1700

Data Index: 166928 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7647. Min Act: -0.1700

Data Index: 7519660 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7207. Min Act: -0.1700

Data Index: 8009324 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7236. Min Act: -0.1700

Data Index: 5175120 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7207. Min Act: -0.1700

Data Index: 2704329 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7224. Min Act: -0.1700

Data Index: 4642795 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7377. Min Act: -0.1700

Data Index: 7284598 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7377. Min Act: -0.1700

Data Index: 7274860 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7318. Min Act: -0.1700

Data Index: 6299697 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.6988. Min Act: -0.1700

Data Index: 2557957 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7189. Min Act: -0.1700

Data Index: 5502071 (Open Web Text)

Max Activating Token Index: 6