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

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

Neuron 797 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.4078. Min Act: -0.0001

Data Index: 177132 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3545. Min Act: -0.0001

Data Index: 353085 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3387. Min Act: -0.0001

Data Index: 960083 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3366. Min Act: -0.0001

Data Index: 995420 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1236969 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3172. Min Act: -0.0001

Data Index: 2452 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3007. Min Act: -0.0001

Data Index: 572730 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3204. Min Act: -0.0001

Data Index: 520996 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3176. Min Act: -0.0001

Data Index: 893544 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2958. Min Act: -0.0001

Data Index: 800695 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2992. Min Act: -0.0001

Data Index: 160113 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2964. Min Act: -0.0001

Data Index: 568079 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.3012. Min Act: -0.0001

Data Index: 313644 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2808. Min Act: -0.0001

Data Index: 937390 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2812. Min Act: -0.0001

Data Index: 301103 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2617. Min Act: -0.0001

Data Index: 383034 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2858. Min Act: -0.0001

Data Index: 236717 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2522. Min Act: -0.0001

Data Index: 785815 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2613. Min Act: -0.0001

Data Index: 64362 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.4078. Min Range: -0.4078

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1240923 (C4 (Web Text))

Max Activating Token Index: 832