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

Dataset: Open Web Text

Neuron 126 in Layer 3

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: 3.3078. Min Range: -3.3078

Max Act: 3.3078. Min Act: -0.1700

Data Index: 5725260 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2829. Min Act: -0.1700

Data Index: 8501468 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2938. Min Act: -0.1700

Data Index: 3442110 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2663. Min Act: -0.1700

Data Index: 8259198 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2702. Min Act: -0.1700

Data Index: 6297192 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2576. Min Act: -0.1700

Data Index: 7028874 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2705. Min Act: -0.1700

Data Index: 5258604 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1263465 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2280. Min Act: -0.1700

Data Index: 3654229 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2306. Min Act: -0.1700

Data Index: 5105234 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2540. Min Act: -0.1700

Data Index: 905141 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1935. Min Act: -0.1700

Data Index: 4209776 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2121. Min Act: -0.1700

Data Index: 1450398 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2306. Min Act: -0.1700

Data Index: 8476748 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2306. Min Act: -0.1700

Data Index: 2880902 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.1957. Min Act: -0.1700

Data Index: 4215242 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2306. Min Act: -0.1700

Data Index: 6949789 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2205. Min Act: -0.1700

Data Index: 6860990 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2451. Min Act: -0.1700

Data Index: 5916576 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.3078. Min Range: -3.3078

Max Act: 3.2264. Min Act: -0.1700

Data Index: 1996838 (Open Web Text)

Max Activating Token Index: 4