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

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

Neuron 2347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1303195 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5964. Min Act: -0.0001

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5550. Min Act: -0.0001

Data Index: 164754 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5855. Min Act: -0.0001

Data Index: 407433 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5249. Min Act: -0.0001

Data Index: 722485 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5285. Min Act: -0.0001

Data Index: 642202 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1338022 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5387. Min Act: -0.0001

Data Index: 937508 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1200835 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5194. Min Act: -0.0001

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1233631 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5142. Min Act: -0.0001

Data Index: 280935 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5113. Min Act: -0.0001

Data Index: 933868 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5272. Min Act: -0.0001

Data Index: 611336 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1232967 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5337. Min Act: -0.0001

Data Index: 876859 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5378. Min Act: -0.0001

Data Index: 613260 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.4852. Min Act: -0.0001

Data Index: 885695 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1291111 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.5964. Min Range: -0.5964

Max Act: 0.5298. Min Act: -0.0001

Data Index: 187527 (C4 (Web Text))

Max Activating Token Index: 88