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

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

Neuron 4610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4993. Min Act: -0.0000

Data Index: 538797 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1259552 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1210951 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3473. Min Act: -0.0000

Data Index: 875498 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3490. Min Act: -0.0000

Data Index: 70719 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3381. Min Act: -0.0000

Data Index: 953411 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3333. Min Act: -0.0000

Data Index: 247997 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3283. Min Act: -0.0000

Data Index: 805764 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1007809 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3273. Min Act: -0.0000

Data Index: 770069 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3287. Min Act: -0.0000

Data Index: 292586 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3253. Min Act: -0.0000

Data Index: 827201 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3352. Min Act: -0.0000

Data Index: 338435 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3327. Min Act: -0.0000

Data Index: 881125 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3062. Min Act: -0.0000

Data Index: 532955 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3143. Min Act: -0.0000

Data Index: 495490 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3255. Min Act: -0.0000

Data Index: 576576 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3112. Min Act: -0.0000

Data Index: 1232695 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.3039. Min Act: -0.0000

Data Index: 568809 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.4993. Min Range: -0.4993

Max Act: 0.2887. Min Act: -0.0000

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 145