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

Dataset: The Pile

Neuron 4088 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1397930 (The Pile)

Max Activating Token Index: 440

Text #1

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4141. Min Act: 0.0000

Data Index: 1464383 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3496. Min Act: -0.0000

Data Index: 985427 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3489. Min Act: -0.0000

Data Index: 348553 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1208238 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1093302 (The Pile)

Max Activating Token Index: 909

Text #6

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3454. Min Act: -0.0000

Data Index: 464695 (The Pile)

Max Activating Token Index: 77

Text #7

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3469. Min Act: -0.0000

Data Index: 603537 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1519741 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3325. Min Act: -0.0000

Data Index: 499066 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3030. Min Act: -0.0000

Data Index: 1280102 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1279002 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1465065 (The Pile)

Max Activating Token Index: 289

Text #13

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1857386 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3099. Min Act: -0.0000

Data Index: 623485 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3245. Min Act: -0.0000

Data Index: 650964 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1781777 (The Pile)

Max Activating Token Index: 584

Text #17

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1013080 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2784. Min Act: -0.0000

Data Index: 986178 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.2934. Min Act: 0.0000

Data Index: 307945 (The Pile)

Max Activating Token Index: 796