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

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

Neuron 4356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.3124. Min Act: -0.0000

Data Index: 146411 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.3099. Min Act: -0.0000

Data Index: 417835 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2953. Min Act: -0.0000

Data Index: 335646 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1246719 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2579. Min Act: -0.0000

Data Index: 77441 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2653. Min Act: -0.0000

Data Index: 64037 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2533. Min Act: -0.0000

Data Index: 877075 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2323. Min Act: -0.0000

Data Index: 797294 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2489. Min Act: -0.0000

Data Index: 704696 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2440. Min Act: -0.0000

Data Index: 774133 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2407. Min Act: -0.0000

Data Index: 410754 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2303. Min Act: -0.0000

Data Index: 549366 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2434. Min Act: -0.0000

Data Index: 905562 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1162443 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1151349 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2298. Min Act: -0.0000

Data Index: 38135 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2371. Min Act: -0.0000

Data Index: 877202 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1028817 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1327345 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.3124. Min Range: -0.3124

Max Act: 0.2298. Min Act: -0.0000

Data Index: 974668 (C4 (Web Text))

Max Activating Token Index: 664