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

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

Neuron 4696 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: 0.5971. Min Range: -0.5971

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1122154 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5919. Min Act: -0.0001

Data Index: 233042 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5869. Min Act: -0.0001

Data Index: 1163180 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5971. Min Act: -0.0001

Data Index: 227180 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5544. Min Act: -0.0001

Data Index: 261312 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5401. Min Act: -0.0001

Data Index: 269598 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5737. Min Act: -0.0001

Data Index: 450408 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5221. Min Act: -0.0001

Data Index: 266190 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5543. Min Act: -0.0001

Data Index: 193363 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5167. Min Act: -0.0001

Data Index: 37423 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5136. Min Act: -0.0001

Data Index: 20959 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5267. Min Act: -0.0001

Data Index: 274158 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5019. Min Act: -0.0001

Data Index: 1170830 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.5066. Min Act: -0.0001

Data Index: 383467 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4866. Min Act: -0.0001

Data Index: 26301 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1166236 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4612. Min Act: -0.0001

Data Index: 701296 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4585. Min Act: -0.0001

Data Index: 717516 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4272. Min Act: -0.0001

Data Index: 538816 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.5971. Min Range: -0.5971

Max Act: 0.4286. Min Act: -0.0001

Data Index: 652136 (C4 (Web Text))

Max Activating Token Index: 82