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

Dataset: The Pile

Neuron 558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0000

Data Index: 556634 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1960925 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3230. Min Act: -0.0000

Data Index: 1301744 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3183. Min Act: -0.0000

Data Index: 300639 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3039. Min Act: -0.0000

Data Index: 93105 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2752. Min Act: -0.0000

Data Index: 343166 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1323173 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3182. Min Act: -0.0000

Data Index: 980925 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1954897 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1343148 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2873. Min Act: -0.0000

Data Index: 470071 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2614. Min Act: -0.0000

Data Index: 715267 (The Pile)

Max Activating Token Index: 542

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2569. Min Act: -0.0000

Data Index: 1634905 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1523780 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2502. Min Act: -0.0000

Data Index: 589333 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2522. Min Act: -0.0000

Data Index: 911322 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1022121 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1476387 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2331. Min Act: -0.0000

Data Index: 923240 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2378. Min Act: -0.0000

Data Index: 695546 (The Pile)

Max Activating Token Index: 788