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

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

Neuron 4263 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0672. Min Act: -0.0001

Data Index: 939538 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9950. Min Act: -0.0001

Data Index: 214577 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9710. Min Act: -0.0001

Data Index: 1081099 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9348. Min Act: -0.0001

Data Index: 1160885 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7947. Min Act: -0.0001

Data Index: 841419 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8126. Min Act: -0.0001

Data Index: 1104634 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7671. Min Act: -0.0001

Data Index: 1113296 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7810. Min Act: -0.0001

Data Index: 184315 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1199510 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7251. Min Act: -0.0001

Data Index: 1310884 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1230826 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8450. Min Act: -0.0001

Data Index: 173846 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7701. Min Act: -0.0001

Data Index: 52972 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1004911 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7339. Min Act: -0.0001

Data Index: 288115 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7181. Min Act: -0.0001

Data Index: 450405 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.6938. Min Act: -0.0001

Data Index: 1254901 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7085. Min Act: -0.0001

Data Index: 1129450 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7179. Min Act: -0.0001

Data Index: 824304 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.7174. Min Act: -0.0001

Data Index: 154481 (C4 (Web Text))

Max Activating Token Index: 459