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

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

Neuron 3069 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: 1.3493. Min Range: -1.3493

Max Act: 1.3493. Min Act: -0.0000

Data Index: 805776 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 1.3493. Min Range: -1.3493

Max Act: 1.0278. Min Act: -0.0000

Data Index: 325927 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1023273 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1211366 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8596. Min Act: -0.0000

Data Index: 537506 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8542. Min Act: -0.0000

Data Index: 1026034 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8270. Min Act: -0.0000

Data Index: 272896 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8443. Min Act: -0.0000

Data Index: 689803 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1305573 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8073. Min Act: -0.0000

Data Index: 321427 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8357. Min Act: 0.0000

Data Index: 145526 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1125689 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.8276. Min Act: -0.0000

Data Index: 841103 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1003472 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.6564. Min Act: -0.0000

Data Index: 820577 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7887. Min Act: -0.0000

Data Index: 234074 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7372. Min Act: -0.0000

Data Index: 827335 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1154175 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7260. Min Act: -0.0000

Data Index: 694010 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.3493. Min Range: -1.3493

Max Act: 0.7181. Min Act: -0.0000

Data Index: 705564 (C4 (Web Text))

Max Activating Token Index: 74