Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7983. Min Act: -0.0000

Data Index: 275748 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1020873 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1046187 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7307. Min Act: -0.0000

Data Index: 151822 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1163443 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7193. Min Act: -0.0000

Data Index: 581767 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7771. Min Act: -0.0000

Data Index: 203607 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7024. Min Act: -0.0000

Data Index: 626525 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7369. Min Act: -0.0000

Data Index: 134748 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6878. Min Act: -0.0000

Data Index: 282704 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.7092. Min Act: -0.0000

Data Index: 765283 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6302. Min Act: -0.0000

Data Index: 181514 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6174. Min Act: -0.0000

Data Index: 515646 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6118. Min Act: -0.0000

Data Index: 825568 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6290. Min Act: -0.0000

Data Index: 418223 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1217961 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1149234 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.5992. Min Act: -0.0000

Data Index: 670328 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.5703. Min Act: -0.0000

Data Index: 220486 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.8372. Min Range: -0.8372

Max Act: 0.5435. Min Act: -0.0000

Data Index: 788067 (C4 (Web Text))

Max Activating Token Index: 128