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

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

Neuron 3604 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4972. Min Act: -0.0002

Data Index: 1271710 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4422. Min Act: -0.0002

Data Index: 42051 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4432. Min Act: -0.0002

Data Index: 812272 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4176. Min Act: -0.0002

Data Index: 1357615 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4140. Min Act: -0.0002

Data Index: 132789 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.4140. Min Act: -0.0002

Data Index: 455709 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3347. Min Act: -0.0002

Data Index: 491055 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3682. Min Act: -0.0002

Data Index: 110863 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3280. Min Act: -0.0002

Data Index: 298072 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3170. Min Act: -0.0002

Data Index: 517168 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3767. Min Act: -0.0002

Data Index: 599510 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3020. Min Act: -0.0002

Data Index: 414572 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3126. Min Act: -0.0002

Data Index: 840704 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.3037. Min Act: -0.0002

Data Index: 518225 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2666. Min Act: -0.0003

Data Index: 1133411 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2467. Min Act: -0.0002

Data Index: 1334304 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2772. Min Act: -0.0002

Data Index: 928056 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2975. Min Act: -0.0002

Data Index: 138348 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2412. Min Act: -0.0002

Data Index: 1101422 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.4972. Min Range: -1.4972

Max Act: 1.2392. Min Act: -0.0002

Data Index: 1221159 (C4 (Web Text))

Max Activating Token Index: 722