Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4800 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6929. Min Act: -0.0000

Data Index: 33902 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6795. Min Act: -0.0000

Data Index: 87160 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1173427 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6990. Min Act: -0.0000

Data Index: 518230 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6729. Min Act: -0.0000

Data Index: 447459 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6953. Min Act: -0.0000

Data Index: 10176 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6503. Min Act: -0.0000

Data Index: 214496 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1105031 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6250. Min Act: -0.0000

Data Index: 40005 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6414. Min Act: -0.0000

Data Index: 918689 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6177. Min Act: -0.0000

Data Index: 878371 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1116394 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6396. Min Act: -0.0000

Data Index: 275532 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6143. Min Act: -0.0000

Data Index: 356525 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6082. Min Act: -0.0000

Data Index: 189125 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6057. Min Act: -0.0000

Data Index: 587936 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6011. Min Act: -0.0000

Data Index: 831153 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6009. Min Act: -0.0000

Data Index: 16176 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.6034. Min Act: -0.0000

Data Index: 949367 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.6990. Min Range: -0.6990

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1269236 (C4 (Web Text))

Max Activating Token Index: 641