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

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

Neuron 3254 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3348. Min Range: -1.3348

Max Act: 1.3348. Min Act: -0.0000

Data Index: 11976 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.3348. Min Range: -1.3348

Max Act: 1.1018. Min Act: -0.0000

Data Index: 701610 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9647. Min Act: -0.0000

Data Index: 1083625 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1216572 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9141. Min Act: -0.0000

Data Index: 458187 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9541. Min Act: 0.0000

Data Index: 851132 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9167. Min Act: -0.0000

Data Index: 862789 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9481. Min Act: -0.0000

Data Index: 214340 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1345077 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1009923 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8695. Min Act: -0.0000

Data Index: 3364 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8848. Min Act: -0.0000

Data Index: 861420 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8885. Min Act: -0.0000

Data Index: 740223 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8536. Min Act: -0.0000

Data Index: 782102 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1163410 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8155. Min Act: -0.0000

Data Index: 468800 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8266. Min Act: -0.0000

Data Index: 586087 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8266. Min Act: -0.0000

Data Index: 595818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.8143. Min Act: -0.0000

Data Index: 234684 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.3348. Min Range: -1.3348

Max Act: 0.7636. Min Act: -0.0000

Data Index: 278207 (C4 (Web Text))

Max Activating Token Index: 552