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

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

Neuron 1212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1429. Min Range: -4.1429

Max Act: 4.1429. Min Act: -0.0000

Data Index: 234998 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 4.1429. Min Range: -4.1429

Max Act: 3.4792. Min Act: -0.0000

Data Index: 776618 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 4.1429. Min Range: -4.1429

Max Act: 3.3452. Min Act: -0.0000

Data Index: 1194126 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 4.1429. Min Range: -4.1429

Max Act: 3.1934. Min Act: -0.0000

Data Index: 362874 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 4.1429. Min Range: -4.1429

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1117237 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.9411. Min Act: -0.0000

Data Index: 808223 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 4.1429. Min Range: -4.1429

Max Act: 3.0106. Min Act: -0.0000

Data Index: 896027 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.9205. Min Act: -0.0000

Data Index: 434171 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.8715. Min Act: -0.0000

Data Index: 1100349 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.6668. Min Act: -0.0000

Data Index: 554793 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.7853. Min Act: -0.0000

Data Index: 722514 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.9223. Min Act: -0.0000

Data Index: 963352 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.5957. Min Act: -0.0000

Data Index: 1040790 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1286900 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.6866. Min Act: -0.0000

Data Index: 57047 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.4153. Min Act: -0.0000

Data Index: 208988 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.7879. Min Act: -0.0000

Data Index: 1072662 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.6263. Min Act: -0.0000

Data Index: 698371 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.6000. Min Act: -0.0000

Data Index: 783598 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 4.1429. Min Range: -4.1429

Max Act: 2.4750. Min Act: -0.0000

Data Index: 296750 (C4 (Web Text))

Max Activating Token Index: 830