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

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

Neuron 5884 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: 1.7231. Min Range: -1.7231

Max Act: 1.7013. Min Act: -0.0002

Data Index: 349751 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.7231. Min Act: -0.0002

Data Index: 750134 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.6582. Min Act: -0.0002

Data Index: 320012 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.5112. Min Act: -0.0002

Data Index: 499968 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4250. Min Act: -0.0002

Data Index: 1015646 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3932. Min Act: -0.0002

Data Index: 1195124 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3992. Min Act: -0.0002

Data Index: 540998 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3893. Min Act: -0.0002

Data Index: 1096256 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4479. Min Act: -0.0002

Data Index: 892435 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3953. Min Act: -0.0002

Data Index: 632548 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.4039. Min Act: -0.0002

Data Index: 166476 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3991. Min Act: -0.0002

Data Index: 867130 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3660. Min Act: -0.0002

Data Index: 994297 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3647. Min Act: -0.0002

Data Index: 743569 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3229. Min Act: -0.0002

Data Index: 694732 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3348. Min Act: -0.0002

Data Index: 607029 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3441. Min Act: -0.0002

Data Index: 469084 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3075. Min Act: -0.0002

Data Index: 1087256 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.3829. Min Act: -0.0002

Data Index: 390990 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.7231. Min Range: -1.7231

Max Act: 1.2978. Min Act: -0.0002

Data Index: 101640 (C4 (Web Text))

Max Activating Token Index: 72