Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.6065. Min Act: -0.0002

Data Index: 506378 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.4743. Min Act: -0.0002

Data Index: 606282 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3474. Min Act: -0.0002

Data Index: 1139208 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3193. Min Act: -0.0002

Data Index: 371810 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3427. Min Act: -0.0002

Data Index: 999683 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.3150. Min Act: -0.0002

Data Index: 671109 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2936. Min Act: -0.0002

Data Index: 464491 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2750. Min Act: -0.0002

Data Index: 685098 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2476. Min Act: -0.0002

Data Index: 98139 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2610. Min Act: -0.0002

Data Index: 885878 (C4 (Web Text))

Max Activating Token Index: 48

Text #10

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2641. Min Act: -0.0002

Data Index: 795709 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2449. Min Act: -0.0002

Data Index: 469337 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2464. Min Act: -0.0002

Data Index: 1117650 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2323. Min Act: -0.0002

Data Index: 914736 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2088. Min Act: -0.0002

Data Index: 80530 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2185. Min Act: -0.0002

Data Index: 926262 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.1938. Min Act: -0.0002

Data Index: 817736 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2184. Min Act: -0.0002

Data Index: 60358 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2082. Min Act: -0.0002

Data Index: 39147 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 1.6065. Min Range: -1.6065

Max Act: 1.2088. Min Act: -0.0002

Data Index: 323707 (C4 (Web Text))

Max Activating Token Index: 229