Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.5168. Min Act: -0.0000

Data Index: 900809 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.3762. Min Act: -0.0000

Data Index: 704817 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.2243. Min Act: -0.0000

Data Index: 396009 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.2704. Min Act: -0.0000

Data Index: 809806 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.1476. Min Act: -0.0000

Data Index: 882161 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.2434. Min Act: -0.0000

Data Index: 85301 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.3591. Min Act: -0.0000

Data Index: 1000207 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.2344. Min Act: -0.0000

Data Index: 901793 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.3350. Min Act: -0.0000

Data Index: 826940 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.0296. Min Act: -0.0000

Data Index: 567809 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.0076. Min Act: -0.0000

Data Index: 1199928 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.2229. Min Act: -0.0000

Data Index: 923016 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.1863. Min Act: -0.0000

Data Index: 741618 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.1082. Min Act: -0.0000

Data Index: 556899 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.5168. Min Range: -2.5168

Max Act: 1.9515. Min Act: -0.0000

Data Index: 19186 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.0451. Min Act: -0.0000

Data Index: 524648 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 2.5168. Min Range: -2.5168

Max Act: 2.0933. Min Act: -0.0000

Data Index: 1278299 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.5168. Min Range: -2.5168

Max Act: 1.8081. Min Act: -0.0000

Data Index: 437821 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.5168. Min Range: -2.5168

Max Act: 1.8085. Min Act: -0.0000

Data Index: 849287 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.5168. Min Range: -2.5168

Max Act: 1.9530. Min Act: -0.0000

Data Index: 1298864 (C4 (Web Text))

Max Activating Token Index: 624