Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 450 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0002

Data Index: 910506 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1152680 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0496. Min Act: -0.0002

Data Index: 343786 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0497. Min Act: -0.0001

Data Index: 238323 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1078769 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0477. Min Act: -0.0002

Data Index: 90766 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0469. Min Act: -0.0002

Data Index: 817529 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0461. Min Act: -0.0002

Data Index: 931811 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1350124 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1228567 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0449. Min Act: -0.0002

Data Index: 858229 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0463. Min Act: -0.0002

Data Index: 754083 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0446. Min Act: -0.0001

Data Index: 810028 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0459. Min Act: -0.0001

Data Index: 571783 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0002

Data Index: 38914 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0002

Data Index: 166992 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0435. Min Act: -0.0002

Data Index: 917392 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0425. Min Act: -0.0002

Data Index: 638174 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0439. Min Act: -0.0002

Data Index: 815408 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0421. Min Act: -0.0002

Data Index: 950584 (C4 (Web Text))

Max Activating Token Index: 62