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

Dataset: The Pile

Neuron 661 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: 1.2003. Min Range: -1.2003

Max Act: 1.2003. Min Act: -0.0000

Data Index: 281661 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1648. Min Act: -0.0000

Data Index: 846438 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1484. Min Act: -0.0000

Data Index: 480377 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1195869 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.1560. Min Act: -0.0000

Data Index: 894937 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0363. Min Act: -0.0000

Data Index: 613291 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9754. Min Act: -0.0000

Data Index: 502729 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0230. Min Act: -0.0000

Data Index: 373729 (The Pile)

Max Activating Token Index: 1014

Text #8

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9825. Min Act: -0.0000

Data Index: 985779 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1006483 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8318. Min Act: -0.0000

Data Index: 293242 (The Pile)

Max Activating Token Index: 148

Text #11

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9000. Min Act: -0.0000

Data Index: 614663 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1182932 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1494825 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8074. Min Act: -0.0000

Data Index: 197157 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9403. Min Act: -0.0000

Data Index: 965314 (The Pile)

Max Activating Token Index: 259

Text #16

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1555668 (The Pile)

Max Activating Token Index: 174

Text #17

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1516532 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1115985 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1452348 (The Pile)

Max Activating Token Index: 233