Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.3079. Min Act: -0.0000

Data Index: 754037 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2969. Min Act: -0.0000

Data Index: 787178 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1214181 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2789. Min Act: -0.0000

Data Index: 46360 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2709. Min Act: -0.0000

Data Index: 612487 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1068014 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2576. Min Act: -0.0001

Data Index: 1331358 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2519. Min Act: -0.0001

Data Index: 525808 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2522. Min Act: -0.0000

Data Index: 533260 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2492. Min Act: 0.0000

Data Index: 149965 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2429. Min Act: 0.0000

Data Index: 464707 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2326. Min Act: -0.0000

Data Index: 118133 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2440. Min Act: -0.0000

Data Index: 431803 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2344. Min Act: -0.0000

Data Index: 587203 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2323. Min Act: -0.0000

Data Index: 867310 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2365. Min Act: -0.0001

Data Index: 470330 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2498. Min Act: -0.0000

Data Index: 415135 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1291780 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2309. Min Act: 0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.3079. Min Range: -0.3079

Max Act: 0.2237. Min Act: -0.0000

Data Index: 51211 (C4 (Web Text))

Max Activating Token Index: 829