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

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

Neuron 3858 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: 1.6257. Min Range: -1.6257

Max Act: 1.6257. Min Act: -0.0002

Data Index: 986931 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5788. Min Act: -0.0002

Data Index: 1224441 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5752. Min Act: -0.0002

Data Index: 129839 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5228. Min Act: -0.0002

Data Index: 477853 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5033. Min Act: -0.0002

Data Index: 1073373 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5022. Min Act: -0.0002

Data Index: 855259 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.5188. Min Act: -0.0002

Data Index: 392821 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4787. Min Act: -0.0002

Data Index: 1310615 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4929. Min Act: -0.0002

Data Index: 1036919 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.3982. Min Act: -0.0002

Data Index: 410572 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4521. Min Act: -0.0002

Data Index: 246664 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4403. Min Act: -0.0002

Data Index: 1212266 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4508. Min Act: -0.0002

Data Index: 309110 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4060. Min Act: -0.0002

Data Index: 498558 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.3925. Min Act: -0.0002

Data Index: 232205 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.3973. Min Act: -0.0002

Data Index: 849576 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4423. Min Act: -0.0002

Data Index: 961298 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.4208. Min Act: -0.0002

Data Index: 651420 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.3973. Min Act: -0.0002

Data Index: 1040104 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.6257. Min Range: -1.6257

Max Act: 1.3503. Min Act: -0.0002

Data Index: 466309 (C4 (Web Text))

Max Activating Token Index: 260