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

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

Neuron 2556 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: 0.2555. Min Range: -0.2555

Max Act: 0.2555. Min Act: -0.0002

Data Index: 283706 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2486. Min Act: -0.0002

Data Index: 263092 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2461. Min Act: -0.0002

Data Index: 65130 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2324. Min Act: -0.0002

Data Index: 639439 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2236. Min Act: -0.0002

Data Index: 11987 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2251. Min Act: -0.0002

Data Index: 1118318 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2134. Min Act: -0.0002

Data Index: 602118 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2123. Min Act: -0.0002

Data Index: 1292743 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2127. Min Act: -0.0002

Data Index: 1280963 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2141. Min Act: -0.0002

Data Index: 398670 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2107. Min Act: -0.0002

Data Index: 200395 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2051. Min Act: -0.0002

Data Index: 1124567 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2058. Min Act: -0.0002

Data Index: 373005 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2037. Min Act: -0.0003

Data Index: 70817 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2041. Min Act: -0.0002

Data Index: 197665 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2035. Min Act: -0.0002

Data Index: 1159741 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2024. Min Act: -0.0003

Data Index: 731372 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2052. Min Act: -0.0003

Data Index: 258654 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.2000. Min Act: -0.0002

Data Index: 400421 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.2555. Min Range: -0.2555

Max Act: 0.1970. Min Act: -0.0002

Data Index: 661290 (C4 (Web Text))

Max Activating Token Index: 580