Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2304 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3834. Min Act: -0.0000

Data Index: 429321 (The Pile)

Max Activating Token Index: 256

Text #1

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1460835 (The Pile)

Max Activating Token Index: 994

Text #2

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3320. Min Act: -0.0000

Data Index: 89757 (The Pile)

Max Activating Token Index: 349

Text #3

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1258589 (The Pile)

Max Activating Token Index: 998

Text #4

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3369. Min Act: -0.0000

Data Index: 33946 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3257. Min Act: -0.0000

Data Index: 69141 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1294056 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1778054 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1297196 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1940925 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1885798 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1644741 (The Pile)

Max Activating Token Index: 335

Text #12

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1938126 (The Pile)

Max Activating Token Index: 660

Text #13

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1609157 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2956. Min Act: -0.0000

Data Index: 623857 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1634240 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3066. Min Act: -0.0000

Data Index: 1056571 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3029. Min Act: -0.0000

Data Index: 150293 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.3153. Min Act: -0.0000

Data Index: 875129 (The Pile)

Max Activating Token Index: 12

Text #19

Max Range: 0.3991. Min Range: -0.3991

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1860880 (The Pile)

Max Activating Token Index: 565