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

Dataset: The Pile

Neuron 2250 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1111742 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1455771 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3591. Min Act: -0.0000

Data Index: 315490 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1363185 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1733591 (The Pile)

Max Activating Token Index: 699

Text #5

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3489. Min Act: -0.0000

Data Index: 514115 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3570. Min Act: -0.0000

Data Index: 308785 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3425. Min Act: -0.0000

Data Index: 1966647 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1705827 (The Pile)

Max Activating Token Index: 183

Text #9

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1396473 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3224. Min Act: -0.0000

Data Index: 173617 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1880750 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2950. Min Act: -0.0000

Data Index: 148234 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3150. Min Act: -0.0000

Data Index: 1924635 (The Pile)

Max Activating Token Index: 80

Text #14

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3005. Min Act: -0.0000

Data Index: 530933 (The Pile)

Max Activating Token Index: 595

Text #15

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1976912 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2939. Min Act: -0.0000

Data Index: 899620 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1081360 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1840419 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.5421. Min Range: -0.5421

Max Act: 0.3080. Min Act: -0.0000

Data Index: 761978 (The Pile)

Max Activating Token Index: 340