Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2457 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.8714. Min Act: -0.0000

Data Index: 1498624 (Python Code)

Max Activating Token Index: 200

Text #1

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.7252. Min Act: -0.0001

Data Index: 635786 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.9343. Min Act: -0.0001

Data Index: 543737 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.5892. Min Act: -0.0000

Data Index: 171587 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.6619. Min Act: -0.0000

Data Index: 963678 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.8489. Min Act: -0.0000

Data Index: 370328 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.6507. Min Act: -0.0001

Data Index: 765549 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1226269 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.4744. Min Act: -0.0000

Data Index: 516117 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.4636. Min Act: -0.0000

Data Index: 1432978 (Python Code)

Max Activating Token Index: 280

Text #10

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.5506. Min Act: -0.0001

Data Index: 345813 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 2.0596. Min Range: -2.0596

Max Act: 2.0596. Min Act: -0.0000

Data Index: 384828 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1110981 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.7151. Min Act: -0.0001

Data Index: 61733 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.4271. Min Act: -0.0000

Data Index: 787967 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1211003 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.5310. Min Act: -0.0000

Data Index: 1099828 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.5932. Min Act: -0.0001

Data Index: 1531671 (Python Code)

Max Activating Token Index: 641

Text #18

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.4235. Min Act: -0.0001

Data Index: 429369 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 2.0596. Min Range: -2.0596

Max Act: 1.6532. Min Act: -0.0000

Data Index: 1493116 (Python Code)

Max Activating Token Index: 21