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

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

Neuron 2109 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1425255 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0407. Min Act: -0.0001

Data Index: 876472 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0360. Min Act: -0.0001

Data Index: 544074 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0356. Min Act: -0.0001

Data Index: 587064 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0359. Min Act: -0.0001

Data Index: 250191 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1257923 (C4 (Web Text))

Max Activating Token Index: 442

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0332. Min Act: -0.0001

Data Index: 654892 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0331. Min Act: -0.0001

Data Index: 578663 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1241777 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1026963 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1150017 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0319. Min Act: -0.0001

Data Index: 672845 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0316. Min Act: -0.0001

Data Index: 993725 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1161360 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0328. Min Act: -0.0001

Data Index: 625806 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0326. Min Act: -0.0001

Data Index: 544076 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0321. Min Act: -0.0001

Data Index: 101753 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0331. Min Act: -0.0001

Data Index: 1169662 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1049993 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0319. Min Act: -0.0001

Data Index: 352066 (C4 (Web Text))

Max Activating Token Index: 252