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

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

Neuron 4689 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.7215. Min Act: -0.0000

Data Index: 970964 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.8418. Min Act: -0.0000

Data Index: 1331673 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.3274. Min Act: -0.0000

Data Index: 909997 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.3464. Min Act: -0.0000

Data Index: 133673 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.4652. Min Act: -0.0000

Data Index: 14611 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.9657. Min Act: -0.0000

Data Index: 1324791 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.3066. Min Act: -0.0000

Data Index: 95599 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 6.8418. Min Range: -6.8418

Max Act: 6.0663. Min Act: -0.0000

Data Index: 485705 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.8095. Min Act: -0.0000

Data Index: 1347489 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.7793. Min Act: -0.0000

Data Index: 180013 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.7376. Min Act: -0.0000

Data Index: 338710 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.6947. Min Act: -0.0000

Data Index: 663224 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.4229. Min Act: -0.0000

Data Index: 729996 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.0665. Min Act: -0.0000

Data Index: 100235 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.2338. Min Act: -0.0000

Data Index: 763000 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 6.8418. Min Range: -6.8418

Max Act: 4.9724. Min Act: -0.0000

Data Index: 9538 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 6.8418. Min Range: -6.8418

Max Act: 5.0643. Min Act: -0.0000

Data Index: 16061 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 6.8418. Min Range: -6.8418

Max Act: 4.7907. Min Act: -0.0000

Data Index: 257634 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 6.8418. Min Range: -6.8418

Max Act: 4.1085. Min Act: -0.0000

Data Index: 359875 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 6.8418. Min Range: -6.8418

Max Act: 3.1699. Min Act: -0.0000

Data Index: 219969 (C4 (Web Text))

Max Activating Token Index: 29