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

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

Neuron 4128 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4851. Min Act: -0.0000

Data Index: 559716 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4879. Min Act: -0.0000

Data Index: 159450 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4314. Min Act: -0.0000

Data Index: 171855 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4325. Min Act: -0.0000

Data Index: 1193286 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1209385 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4111. Min Act: -0.0000

Data Index: 392183 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4194. Min Act: -0.0000

Data Index: 410762 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4091. Min Act: -0.0000

Data Index: 79352 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3932. Min Act: -0.0000

Data Index: 301721 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3897. Min Act: -0.0000

Data Index: 57246 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1244846 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3992. Min Act: -0.0000

Data Index: 222834 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3865. Min Act: -0.0000

Data Index: 700229 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3841. Min Act: -0.0000

Data Index: 889142 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3940. Min Act: -0.0000

Data Index: 967074 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3766. Min Act: -0.0000

Data Index: 978772 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1157956 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3705. Min Act: -0.0000

Data Index: 104581 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3790. Min Act: -0.0000

Data Index: 288346 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.4879. Min Range: -0.4879

Max Act: 0.3801. Min Act: -0.0000

Data Index: 47224 (C4 (Web Text))

Max Activating Token Index: 528