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

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

Neuron 1490 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: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 592625 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1936 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.3077. Min Act: -0.0000

Data Index: 691442 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1031329 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2444. Min Act: -0.0001

Data Index: 976157 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2466. Min Act: -0.0000

Data Index: 821666 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2433. Min Act: -0.0000

Data Index: 809498 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2287. Min Act: -0.0001

Data Index: 358184 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2307. Min Act: -0.0000

Data Index: 385562 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2429. Min Act: -0.0001

Data Index: 958245 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1139978 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1161323 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2266. Min Act: -0.0001

Data Index: 253720 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2170. Min Act: -0.0000

Data Index: 69440 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2157. Min Act: -0.0001

Data Index: 918921 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2093. Min Act: -0.0000

Data Index: 434240 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2228. Min Act: -0.0000

Data Index: 407228 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2343. Min Act: -0.0001

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2302. Min Act: -0.0000

Data Index: 147714 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2197. Min Act: -0.0001

Data Index: 176658 (C4 (Web Text))

Max Activating Token Index: 609