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

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

Neuron 1601 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: 1.1129. Min Range: -1.1129

Max Act: 1.1129. Min Act: -0.0001

Data Index: 1317606 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9717. Min Act: -0.0001

Data Index: 287378 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9778. Min Act: -0.0001

Data Index: 195378 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9494. Min Act: -0.0001

Data Index: 574061 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.9195. Min Act: -0.0001

Data Index: 663283 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8101. Min Act: -0.0001

Data Index: 574762 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7977. Min Act: -0.0001

Data Index: 449817 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1014909 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8199. Min Act: -0.0001

Data Index: 582510 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7879. Min Act: -0.0001

Data Index: 651925 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8349. Min Act: -0.0001

Data Index: 839407 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8036. Min Act: -0.0001

Data Index: 39676 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8141. Min Act: -0.0001

Data Index: 428670 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7825. Min Act: -0.0001

Data Index: 317450 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7892. Min Act: -0.0001

Data Index: 218701 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.8671. Min Act: -0.0001

Data Index: 921243 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7839. Min Act: -0.0001

Data Index: 1100824 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7871. Min Act: -0.0001

Data Index: 126530 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7330. Min Act: -0.0001

Data Index: 418944 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.1129. Min Range: -1.1129

Max Act: 0.7288. Min Act: -0.0001

Data Index: 27767 (C4 (Web Text))

Max Activating Token Index: 531