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

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

Neuron 4050 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: 4.0318. Min Range: -4.0318

Max Act: 4.0318. Min Act: -0.0000

Data Index: 1107670 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.9879. Min Act: -0.0000

Data Index: 578810 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.6352. Min Act: -0.0000

Data Index: 1146034 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.5672. Min Act: -0.0000

Data Index: 755625 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.8037. Min Act: -0.0000

Data Index: 293161 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.5133. Min Act: -0.0000

Data Index: 70115 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.4074. Min Act: -0.0000

Data Index: 1019035 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.4969. Min Act: -0.0000

Data Index: 937776 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.3489. Min Act: -0.0000

Data Index: 240834 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.3388. Min Act: -0.0000

Data Index: 613269 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.4306. Min Act: -0.0000

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.4414. Min Act: -0.0000

Data Index: 1039010 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.2925. Min Act: -0.0000

Data Index: 844746 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.3935. Min Act: -0.0000

Data Index: 593901 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.3670. Min Act: -0.0000

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.3297. Min Act: -0.0000

Data Index: 791878 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.0956. Min Act: -0.0000

Data Index: 687024 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.2472. Min Act: -0.0000

Data Index: 970502 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1249653 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 4.0318. Min Range: -4.0318

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1010922 (C4 (Web Text))

Max Activating Token Index: 177