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

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

Neuron 3925 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.6457. Min Act: -0.0001

Data Index: 1189098 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.6202. Min Act: -0.0001

Data Index: 1038252 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5947. Min Act: -0.0001

Data Index: 674893 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5443. Min Act: -0.0001

Data Index: 73442 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5992. Min Act: -0.0001

Data Index: 412998 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5378. Min Act: -0.0001

Data Index: 331540 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5360. Min Act: -0.0001

Data Index: 485067 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5498. Min Act: -0.0001

Data Index: 941417 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5150. Min Act: -0.0001

Data Index: 766857 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5385. Min Act: -0.0001

Data Index: 836953 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5356. Min Act: -0.0001

Data Index: 977314 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5441. Min Act: -0.0001

Data Index: 145504 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1029663 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1228693 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.5512. Min Act: -0.0001

Data Index: 1105575 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4979. Min Act: -0.0001

Data Index: 702632 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4907. Min Act: -0.0001

Data Index: 525220 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4862. Min Act: -0.0001

Data Index: 689866 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4908. Min Act: -0.0001

Data Index: 608567 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.6457. Min Range: -0.6457

Max Act: 0.4594. Min Act: -0.0001

Data Index: 770674 (C4 (Web Text))

Max Activating Token Index: 992