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

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

Neuron 4217 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.9956. Min Act: -0.0000

Data Index: 277222 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.8897. Min Act: -0.0000

Data Index: 475996 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.7585. Min Act: -0.0000

Data Index: 8913 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.6957. Min Act: -0.0000

Data Index: 759654 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.6203. Min Act: -0.0000

Data Index: 475118 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5182. Min Act: -0.0000

Data Index: 315095 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1366256 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4384. Min Act: -0.0000

Data Index: 142654 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4571. Min Act: -0.0000

Data Index: 872897 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1465421 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5145. Min Act: -0.0000

Data Index: 281240 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5210. Min Act: -0.0000

Data Index: 1229242 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5895. Min Act: -0.0000

Data Index: 487556 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4708. Min Act: -0.0000

Data Index: 367851 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4592. Min Act: -0.0000

Data Index: 912833 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4585. Min Act: -0.0000

Data Index: 455118 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1176925 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.3416. Min Act: -0.0000

Data Index: 1133116 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.3600. Min Act: -0.0000

Data Index: 640821 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.9956. Min Range: -1.9956

Max Act: 1.5232. Min Act: -0.0000

Data Index: 1043239 (C4 (Web Text))

Max Activating Token Index: 680