Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4047 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0266. Min Range: -3.0266

Max Act: 3.0266. Min Act: -0.0000

Data Index: 1055550 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.0882. Min Act: -0.0000

Data Index: 1478330 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 3.0266. Min Range: -3.0266

Max Act: 2.0183. Min Act: -0.0000

Data Index: 1816598 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.8935. Min Act: -0.0000

Data Index: 635037 (The Pile)

Max Activating Token Index: 404

Text #4

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.8874. Min Act: -0.0000

Data Index: 1549994 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.4103. Min Act: -0.0000

Data Index: 447246 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1561674 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1935269 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.2263. Min Act: -0.0000

Data Index: 291789 (The Pile)

Max Activating Token Index: 828

Text #9

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.2904. Min Act: -0.0000

Data Index: 170885 (The Pile)

Max Activating Token Index: 344

Text #10

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.3645. Min Act: -0.0000

Data Index: 499108 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.3225. Min Act: -0.0000

Data Index: 222391 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1657969 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1330003 (The Pile)

Max Activating Token Index: 555

Text #14

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.0687. Min Act: -0.0000

Data Index: 169823 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 3.0266. Min Range: -3.0266

Max Act: 0.7233. Min Act: -0.0000

Data Index: 93281 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 3.0266. Min Range: -3.0266

Max Act: 0.9823. Min Act: -0.0000

Data Index: 855524 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 3.0266. Min Range: -3.0266

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1863595 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.0605. Min Act: -0.0000

Data Index: 322748 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 3.0266. Min Range: -3.0266

Max Act: 1.0187. Min Act: -0.0000

Data Index: 175993 (The Pile)

Max Activating Token Index: 32