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

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

Neuron 3063 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5178. Min Range: -6.5178

Max Act: 6.5178. Min Act: -0.0000

Data Index: 333949 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 6.5178. Min Range: -6.5178

Max Act: 5.2443. Min Act: -0.0000

Data Index: 1228236 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 6.5178. Min Range: -6.5178

Max Act: 5.1855. Min Act: -0.0000

Data Index: 44047 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 6.5178. Min Range: -6.5178

Max Act: 5.2793. Min Act: -0.0001

Data Index: 1260370 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.9109. Min Act: -0.0001

Data Index: 274874 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.7708. Min Act: -0.0001

Data Index: 704170 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.9086. Min Act: -0.0001

Data Index: 1022365 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.8005. Min Act: -0.0000

Data Index: 17084 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.4343. Min Act: -0.0000

Data Index: 491559 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.7574. Min Act: -0.0000

Data Index: 451282 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.5521. Min Act: -0.0001

Data Index: 1235328 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.5496. Min Act: -0.0001

Data Index: 1159329 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.7110. Min Act: -0.0001

Data Index: 382607 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.3596. Min Act: -0.0000

Data Index: 590327 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.7056. Min Act: -0.0001

Data Index: 852140 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.3107. Min Act: -0.0001

Data Index: 402978 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.2991. Min Act: -0.0001

Data Index: 875602 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.4143. Min Act: -0.0000

Data Index: 459232 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.2500. Min Act: -0.0000

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 6.5178. Min Range: -6.5178

Max Act: 4.5510. Min Act: -0.0001

Data Index: 242812 (C4 (Web Text))

Max Activating Token Index: 343