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

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

Neuron 145 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.6942. Min Act: -0.0000

Data Index: 658603 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.5929. Min Act: -0.0000

Data Index: 1346052 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.0432. Min Act: -0.0000

Data Index: 152797 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.3309. Min Act: -0.0000

Data Index: 255778 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.2740. Min Act: -0.0000

Data Index: 990761 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.2826. Min Act: -0.0001

Data Index: 1205859 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.2577. Min Act: -0.0000

Data Index: 359989 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.2205. Min Act: -0.0000

Data Index: 1028871 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.9737. Min Act: -0.0000

Data Index: 1219231 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.1252. Min Act: -0.0000

Data Index: 1287806 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.1105. Min Act: -0.0000

Data Index: 465988 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.9353. Min Act: -0.0001

Data Index: 1014496 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 4.6942. Min Range: -4.6942

Max Act: 4.0444. Min Act: -0.0000

Data Index: 382843 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.6479. Min Act: -0.0001

Data Index: 944999 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.8007. Min Act: -0.0001

Data Index: 1153975 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.7388. Min Act: -0.0000

Data Index: 719371 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.5168. Min Act: -0.0000

Data Index: 238392 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.5412. Min Act: -0.0000

Data Index: 939416 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.3171. Min Act: -0.0000

Data Index: 607788 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 4.6942. Min Range: -4.6942

Max Act: 3.6141. Min Act: -0.0001

Data Index: 1354154 (C4 (Web Text))

Max Activating Token Index: 605