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

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

Neuron 124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0325. Min Range: -2.0325

Max Act: 2.0325. Min Act: -0.0000

Data Index: 176129 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.8910. Min Act: -0.0000

Data Index: 661027 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7985. Min Act: -0.0000

Data Index: 966708 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1100527 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.8846. Min Act: -0.0000

Data Index: 359628 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.8131. Min Act: -0.0000

Data Index: 566643 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7457. Min Act: -0.0000

Data Index: 185514 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.8048. Min Act: -0.0000

Data Index: 649277 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1278712 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7602. Min Act: -0.0000

Data Index: 1191934 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.6814. Min Act: -0.0000

Data Index: 1256648 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7204. Min Act: -0.0000

Data Index: 453239 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.8319. Min Act: -0.0000

Data Index: 956772 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.6984. Min Act: -0.0000

Data Index: 1122467 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.5880. Min Act: -0.0000

Data Index: 314826 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7935. Min Act: -0.0000

Data Index: 84194 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.5495. Min Act: -0.0000

Data Index: 550790 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.5461. Min Act: -0.0000

Data Index: 336530 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.7464. Min Act: -0.0000

Data Index: 1081002 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 2.0325. Min Range: -2.0325

Max Act: 1.6338. Min Act: -0.0000

Data Index: 651685 (C4 (Web Text))

Max Activating Token Index: 527