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

Dataset: The Pile

Neuron 540 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: 0.4252. Min Range: -0.4252

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1396078 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3700. Min Act: 0.0000

Data Index: 989499 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3975. Min Act: -0.0000

Data Index: 293570 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3782. Min Act: -0.0000

Data Index: 167470 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1021035 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3608. Min Act: -0.0000

Data Index: 1014316 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1951725 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1097820 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3383. Min Act: -0.0000

Data Index: 556054 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3116. Min Act: -0.0000

Data Index: 955963 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1989068 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1798195 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3230. Min Act: -0.0000

Data Index: 200870 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1753206 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3151. Min Act: -0.0000

Data Index: 806896 (The Pile)

Max Activating Token Index: 748

Text #15

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1677811 (The Pile)

Max Activating Token Index: 402

Text #16

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3236. Min Act: -0.0000

Data Index: 814356 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3123. Min Act: -0.0000

Data Index: 716318 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1832460 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 0.4252. Min Range: -0.4252

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1056590 (The Pile)

Max Activating Token Index: 959