Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3044 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.4649. Min Act: -0.0001

Data Index: 576404 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1308952 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3637. Min Act: -0.0001

Data Index: 807146 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3915. Min Act: -0.0001

Data Index: 349336 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3532. Min Act: -0.0001

Data Index: 385385 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3424. Min Act: -0.0001

Data Index: 938837 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3380. Min Act: -0.0000

Data Index: 237965 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3365. Min Act: -0.0000

Data Index: 221677 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3468. Min Act: -0.0001

Data Index: 259910 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3184. Min Act: -0.0001

Data Index: 1210991 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3298. Min Act: -0.0001

Data Index: 345794 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3082. Min Act: -0.0001

Data Index: 411452 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3318. Min Act: -0.0001

Data Index: 321316 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3305. Min Act: -0.0001

Data Index: 1227348 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3469. Min Act: -0.0001

Data Index: 909733 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1199582 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3308. Min Act: -0.0001

Data Index: 405927 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3253. Min Act: -0.0001

Data Index: 545628 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1065648 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.4649. Min Range: -0.4649

Max Act: 0.3247. Min Act: -0.0001

Data Index: 195467 (C4 (Web Text))

Max Activating Token Index: 718