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

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

Neuron 3102 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: 0.7829. Min Range: -0.7829

Max Act: 0.7829. Min Act: -0.0001

Data Index: 629362 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7489. Min Act: -0.0001

Data Index: 873118 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7280. Min Act: -0.0001

Data Index: 23654 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7695. Min Act: -0.0001

Data Index: 390978 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6543. Min Act: -0.0001

Data Index: 580999 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6912. Min Act: -0.0001

Data Index: 548608 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6424. Min Act: -0.0001

Data Index: 53846 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6557. Min Act: -0.0001

Data Index: 703542 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6224. Min Act: -0.0001

Data Index: 152961 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6459. Min Act: -0.0001

Data Index: 1023047 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1271541 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1241986 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5976. Min Act: -0.0001

Data Index: 680912 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6380. Min Act: -0.0001

Data Index: 1110062 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1223069 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1173813 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6225. Min Act: -0.0001

Data Index: 325090 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6626. Min Act: -0.0001

Data Index: 657261 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5626. Min Act: -0.0001

Data Index: 891666 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6148. Min Act: -0.0001

Data Index: 237024 (C4 (Web Text))

Max Activating Token Index: 285