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

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

Neuron 1314 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2949. Min Act: -0.0000

Data Index: 579632 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1065800 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2838. Min Act: -0.0000

Data Index: 160916 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1047438 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1123802 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2520. Min Act: -0.0000

Data Index: 500293 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1273111 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2597. Min Act: -0.0000

Data Index: 818011 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2430. Min Act: -0.0000

Data Index: 506410 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2539. Min Act: -0.0000

Data Index: 121335 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1256064 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2453. Min Act: -0.0000

Data Index: 273715 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2414. Min Act: -0.0000

Data Index: 875134 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2391. Min Act: -0.0000

Data Index: 59770 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2382. Min Act: -0.0000

Data Index: 486557 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2312. Min Act: -0.0000

Data Index: 178680 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2316. Min Act: -0.0000

Data Index: 404945 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2403. Min Act: -0.0000

Data Index: 895307 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2263. Min Act: -0.0000

Data Index: 300749 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2263. Min Act: 0.0000

Data Index: 1310772 (C4 (Web Text))

Max Activating Token Index: 443