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

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

Neuron 1903 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: 0.4154. Min Range: -0.4154

Max Act: 0.4154. Min Act: -0.0001

Data Index: 637830 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3786. Min Act: -0.0001

Data Index: 12085 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1027595 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1124638 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3410. Min Act: -0.0000

Data Index: 709038 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3289. Min Act: -0.0001

Data Index: 688901 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3377. Min Act: -0.0001

Data Index: 1137178 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3128. Min Act: -0.0001

Data Index: 307820 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3097. Min Act: -0.0001

Data Index: 1144266 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3213. Min Act: -0.0001

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1087042 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3025. Min Act: -0.0001

Data Index: 848416 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3081. Min Act: -0.0001

Data Index: 52392 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2925. Min Act: -0.0001

Data Index: 535079 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3004. Min Act: -0.0001

Data Index: 806216 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3084. Min Act: -0.0001

Data Index: 970522 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2988. Min Act: -0.0001

Data Index: 130504 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1148145 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.3155. Min Act: -0.0001

Data Index: 1169831 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.4154. Min Range: -0.4154

Max Act: 0.2935. Min Act: -0.0001

Data Index: 813143 (C4 (Web Text))

Max Activating Token Index: 508