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

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

Neuron 2801 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.8242. Min Act: -0.0002

Data Index: 1106588 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7971. Min Act: -0.0002

Data Index: 590188 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7816. Min Act: -0.0003

Data Index: 274119 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7559. Min Act: -0.0002

Data Index: 949384 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7593. Min Act: -0.0002

Data Index: 323957 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7468. Min Act: -0.0002

Data Index: 892079 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7418. Min Act: -0.0002

Data Index: 1095840 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7336. Min Act: -0.0002

Data Index: 655498 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7466. Min Act: -0.0002

Data Index: 289651 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7232. Min Act: -0.0002

Data Index: 253481 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7159. Min Act: -0.0002

Data Index: 1067994 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7162. Min Act: -0.0002

Data Index: 287250 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7349. Min Act: -0.0002

Data Index: 671120 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7119. Min Act: -0.0002

Data Index: 1292522 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7024. Min Act: -0.0002

Data Index: 53880 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7055. Min Act: -0.0002

Data Index: 313084 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6961. Min Act: -0.0002

Data Index: 1133686 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7077. Min Act: -0.0002

Data Index: 399614 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.7073. Min Act: -0.0002

Data Index: 365387 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.8242. Min Range: -0.8242

Max Act: 0.6990. Min Act: -0.0002

Data Index: 761948 (C4 (Web Text))

Max Activating Token Index: 316