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

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

Neuron 895 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: 0.6347. Min Range: -0.6347

Max Act: 0.6347. Min Act: -0.0000

Data Index: 332025 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5518. Min Act: -0.0001

Data Index: 198536 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4769. Min Act: -0.0001

Data Index: 410520 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5157. Min Act: -0.0000

Data Index: 514689 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4714. Min Act: -0.0000

Data Index: 942899 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4585. Min Act: -0.0000

Data Index: 682618 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1014904 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4549. Min Act: -0.0000

Data Index: 714208 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4238. Min Act: -0.0001

Data Index: 637877 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4192. Min Act: -0.0001

Data Index: 796208 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3936. Min Act: -0.0001

Data Index: 235168 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4075. Min Act: -0.0000

Data Index: 76176 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4186. Min Act: -0.0001

Data Index: 434228 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1322263 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3955. Min Act: -0.0000

Data Index: 299646 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4091. Min Act: -0.0001

Data Index: 918409 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3992. Min Act: -0.0001

Data Index: 44957 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3582. Min Act: -0.0000

Data Index: 390911 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3879. Min Act: -0.0001

Data Index: 131885 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3809. Min Act: -0.0001

Data Index: 639908 (C4 (Web Text))

Max Activating Token Index: 789