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

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

Neuron 5091 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.6302. Min Act: -0.0000

Data Index: 791890 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.5424. Min Act: -0.0000

Data Index: 37102 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.6030. Min Act: -0.0000

Data Index: 686391 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.5264. Min Act: -0.0000

Data Index: 776105 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.5574. Min Act: -0.0000

Data Index: 434361 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.4685. Min Act: -0.0000

Data Index: 1053209 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.5390. Min Act: -0.0001

Data Index: 1072092 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.2744. Min Act: -0.0001

Data Index: 205611 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3829. Min Act: -0.0000

Data Index: 1185387 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1290650 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3662. Min Act: -0.0001

Data Index: 1174574 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1223364 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3678. Min Act: -0.0000

Data Index: 367225 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.4312. Min Act: -0.0001

Data Index: 867410 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3192. Min Act: -0.0000

Data Index: 393480 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3947. Min Act: -0.0000

Data Index: 876388 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.4026. Min Act: -0.0001

Data Index: 845530 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.2414. Min Act: -0.0000

Data Index: 478679 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.3801. Min Act: -0.0000

Data Index: 508960 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.6302. Min Range: -1.6302

Max Act: 1.2748. Min Act: -0.0000

Data Index: 538981 (C4 (Web Text))

Max Activating Token Index: 756