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

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

Neuron 3977 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: 1.8735. Min Range: -1.8735

Max Act: 1.8735. Min Act: -0.0003

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.8211. Min Act: -0.0002

Data Index: 278723 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.7938. Min Act: -0.0002

Data Index: 284721 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.7253. Min Act: -0.0002

Data Index: 65357 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6841. Min Act: -0.0002

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.7570. Min Act: -0.0002

Data Index: 326551 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.7303. Min Act: -0.0002

Data Index: 715963 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.7327. Min Act: -0.0002

Data Index: 585264 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6531. Min Act: -0.0002

Data Index: 1015465 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6212. Min Act: -0.0002

Data Index: 582350 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6777. Min Act: -0.0002

Data Index: 509158 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6718. Min Act: -0.0002

Data Index: 637449 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6322. Min Act: -0.0002

Data Index: 1033984 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.5992. Min Act: -0.0003

Data Index: 1243494 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6019. Min Act: -0.0002

Data Index: 1263432 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6182. Min Act: -0.0002

Data Index: 51299 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.6341. Min Act: -0.0002

Data Index: 595223 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.5957. Min Act: -0.0002

Data Index: 850011 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.5886. Min Act: -0.0002

Data Index: 411532 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.8735. Min Range: -1.8735

Max Act: 1.5401. Min Act: -0.0002

Data Index: 242090 (C4 (Web Text))

Max Activating Token Index: 486