Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.3305. Min Act: 0.0000

Data Index: 1114668 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.3050. Min Act: -0.0000

Data Index: 141182 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2985. Min Act: -0.0000

Data Index: 49129 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2933. Min Act: 0.0001

Data Index: 503959 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1020472 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2791. Min Act: -0.0000

Data Index: 202597 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2797. Min Act: -0.0001

Data Index: 639522 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2754. Min Act: -0.0001

Data Index: 887583 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1226350 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2756. Min Act: 0.0001

Data Index: 308726 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2694. Min Act: -0.0001

Data Index: 728994 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2578. Min Act: 0.0000

Data Index: 634788 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1125758 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1208944 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2590. Min Act: -0.0001

Data Index: 909939 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1310132 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2550. Min Act: -0.0001

Data Index: 805681 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2539. Min Act: 0.0001

Data Index: 90178 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2470. Min Act: -0.0000

Data Index: 254335 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.3305. Min Range: -0.3305

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1023740 (C4 (Web Text))

Max Activating Token Index: 286