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

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

Neuron 806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1140965 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4027. Min Act: -0.0001

Data Index: 218101 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4114. Min Act: -0.0000

Data Index: 157940 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4137. Min Act: -0.0000

Data Index: 118440 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4227. Min Act: -0.0001

Data Index: 964596 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1079157 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3594. Min Act: -0.0001

Data Index: 1318751 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1314569 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3831. Min Act: -0.0001

Data Index: 386099 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3592. Min Act: -0.0001

Data Index: 1293382 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3746. Min Act: -0.0001

Data Index: 513809 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3579. Min Act: -0.0001

Data Index: 432873 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3593. Min Act: -0.0001

Data Index: 483343 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3584. Min Act: -0.0001

Data Index: 480287 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3280. Min Act: -0.0001

Data Index: 358273 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3754. Min Act: -0.0001

Data Index: 963147 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3487. Min Act: -0.0000

Data Index: 364392 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3574. Min Act: -0.0000

Data Index: 230550 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3535. Min Act: -0.0001

Data Index: 356554 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4643. Min Range: -0.4643

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1306417 (C4 (Web Text))

Max Activating Token Index: 71