Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2597 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5043. Min Act: -0.0004

Data Index: 325574 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5585. Min Act: -0.0004

Data Index: 935596 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4971. Min Act: -0.0004

Data Index: 165732 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5430. Min Act: -0.0004

Data Index: 1230481 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5418. Min Act: -0.0004

Data Index: 870493 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4879. Min Act: -0.0004

Data Index: 859522 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5175. Min Act: -0.0004

Data Index: 773735 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5349. Min Act: -0.0004

Data Index: 1101009 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4956. Min Act: -0.0004

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5108. Min Act: -0.0004

Data Index: 194304 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4715. Min Act: -0.0004

Data Index: 282510 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5406. Min Act: -0.0004

Data Index: 791833 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4656. Min Act: -0.0004

Data Index: 1022892 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4965. Min Act: -0.0004

Data Index: 902866 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5302. Min Act: -0.0004

Data Index: 1101137 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5121. Min Act: -0.0004

Data Index: 726891 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4748. Min Act: -0.0004

Data Index: 293950 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.4930. Min Act: -0.0004

Data Index: 847616 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5275. Min Act: -0.0004

Data Index: 398971 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.5585. Min Range: -0.5585

Max Act: 0.5448. Min Act: -0.0004

Data Index: 213785 (C4 (Web Text))

Max Activating Token Index: 589