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

Dataset: The Pile

Neuron 2499 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: 0.6942. Min Range: -0.6942

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1826608 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6087. Min Act: -0.0000

Data Index: 1568923 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1726046 (The Pile)

Max Activating Token Index: 954

Text #3

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1402790 (The Pile)

Max Activating Token Index: 937

Text #4

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1602254 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1443064 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1887021 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5196. Min Act: -0.0000

Data Index: 156065 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1965886 (The Pile)

Max Activating Token Index: 87

Text #9

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1170711 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5692. Min Act: -0.0000

Data Index: 593873 (The Pile)

Max Activating Token Index: 270

Text #11

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5847. Min Act: -0.0000

Data Index: 275308 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1188133 (The Pile)

Max Activating Token Index: 796

Text #13

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5757. Min Act: -0.0000

Data Index: 44767 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1086021 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5342. Min Act: -0.0000

Data Index: 418603 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5500. Min Act: -0.0000

Data Index: 100117 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1929314 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5506. Min Act: -0.0000

Data Index: 134280 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.6942. Min Range: -0.6942

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1495429 (The Pile)

Max Activating Token Index: 726