Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3431 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3415. Min Act: -0.0001

Data Index: 898750 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3001. Min Act: -0.0001

Data Index: 969278 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3163. Min Act: -0.0001

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3094. Min Act: -0.0001

Data Index: 161908 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2999. Min Act: -0.0001

Data Index: 392132 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3056. Min Act: -0.0001

Data Index: 594044 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3118. Min Act: -0.0001

Data Index: 748223 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3141. Min Act: -0.0001

Data Index: 1178602 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3150. Min Act: -0.0001

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3033. Min Act: -0.0001

Data Index: 297494 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2788. Min Act: -0.0001

Data Index: 516627 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2866. Min Act: -0.0001

Data Index: 412086 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2878. Min Act: -0.0001

Data Index: 671081 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2841. Min Act: -0.0001

Data Index: 443457 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2958. Min Act: -0.0001

Data Index: 1317859 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2809. Min Act: -0.0001

Data Index: 1148160 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2899. Min Act: -0.0001

Data Index: 1203394 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2711. Min Act: -0.0001

Data Index: 669769 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1044222 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.3415. Min Range: -0.3415

Max Act: 0.2877. Min Act: -0.0001

Data Index: 353952 (C4 (Web Text))

Max Activating Token Index: 966