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

Dataset: Open Web Text

Neuron 2998 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: 4.1133. Min Range: -4.1133

Max Act: 4.1133. Min Act: -0.1700

Data Index: 2653324 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0855. Min Act: -0.1700

Data Index: 1538514 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.1003. Min Act: -0.1700

Data Index: 6766427 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0851. Min Act: -0.1700

Data Index: 5557102 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0543. Min Act: -0.1700

Data Index: 1113114 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0463. Min Act: -0.1700

Data Index: 8670031 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0448. Min Act: -0.1700

Data Index: 2115282 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0570. Min Act: -0.1700

Data Index: 5209779 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0446. Min Act: -0.1700

Data Index: 2117443 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0341. Min Act: -0.1700

Data Index: 2663368 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0345. Min Act: -0.1700

Data Index: 4336893 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0231. Min Act: -0.1700

Data Index: 3852260 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0329. Min Act: -0.1700

Data Index: 5110594 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0270. Min Act: -0.1700

Data Index: 4610073 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9961. Min Act: -0.1700

Data Index: 2460324 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9782. Min Act: -0.1700

Data Index: 4164025 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9804. Min Act: -0.1700

Data Index: 4974053 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9741. Min Act: -0.1700

Data Index: 1767167 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.1133. Min Range: -4.1133

Max Act: 3.9782. Min Act: -0.1700

Data Index: 3843059 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.1133. Min Range: -4.1133

Max Act: 4.0028. Min Act: -0.1700

Data Index: 4481865 (Open Web Text)

Max Activating Token Index: 4