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

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

Neuron 234 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.8343. Min Act: -0.0001

Data Index: 261804 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.5814. Min Act: -0.0001

Data Index: 534866 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.5894. Min Act: -0.0001

Data Index: 347344 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.6384. Min Act: -0.0001

Data Index: 1054570 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.5977. Min Act: -0.0001

Data Index: 835391 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3214. Min Act: -0.0001

Data Index: 846965 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3874. Min Act: -0.0001

Data Index: 452920 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3808. Min Act: -0.0001

Data Index: 1316955 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.2690. Min Act: -0.0001

Data Index: 213512 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.5412. Min Act: -0.0001

Data Index: 579603 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.4283. Min Act: -0.0001

Data Index: 29696 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3314. Min Act: -0.0001

Data Index: 218598 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3302. Min Act: -0.0001

Data Index: 1335917 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3585. Min Act: -0.0001

Data Index: 263558 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.4472. Min Act: -0.0001

Data Index: 674168 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.2863. Min Act: -0.0001

Data Index: 30523 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.4379. Min Act: -0.0001

Data Index: 377335 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3367. Min Act: -0.0001

Data Index: 128538 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.4046. Min Act: -0.0001

Data Index: 263984 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.8343. Min Range: -1.8343

Max Act: 1.3330. Min Act: -0.0001

Data Index: 685317 (C4 (Web Text))

Max Activating Token Index: 741