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

Dataset: The Pile

Neuron 1236 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.6402. Min Act: 0.0000

Data Index: 1293454 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1397600 (The Pile)

Max Activating Token Index: 826

Text #2

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.5253. Min Act: -0.0000

Data Index: 858040 (The Pile)

Max Activating Token Index: 84

Text #3

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3312. Min Act: -0.0000

Data Index: 590908 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4100. Min Act: -0.0000

Data Index: 863067 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3413. Min Act: -0.0000

Data Index: 1356916 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3045. Min Act: -0.0000

Data Index: 707637 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2576. Min Act: -0.0000

Data Index: 910348 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3048. Min Act: -0.0000

Data Index: 439478 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3083. Min Act: -0.0000

Data Index: 343304 (The Pile)

Max Activating Token Index: 241

Text #10

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1946449 (The Pile)

Max Activating Token Index: 328

Text #11

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1711. Min Act: -0.0000

Data Index: 281697 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2412. Min Act: -0.0000

Data Index: 1082544 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1306861 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2331. Min Act: -0.0000

Data Index: 744004 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1468528 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1536272 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1212175 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1116. Min Act: -0.0000

Data Index: 318826 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1859. Min Act: -0.0000

Data Index: 1890035 (The Pile)

Max Activating Token Index: 664