Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5962 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1927. Min Range: -6.1927

Max Act: 6.1927. Min Act: -0.0000

Data Index: 1198597 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.9758. Min Act: -0.0000

Data Index: 982938 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.6536. Min Act: -0.0000

Data Index: 899581 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.4735. Min Act: -0.0000

Data Index: 1006318 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.6444. Min Act: -0.0000

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.5388. Min Act: -0.0000

Data Index: 441442 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.5179. Min Act: -0.0000

Data Index: 333953 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.0310. Min Act: -0.0000

Data Index: 636824 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.8104. Min Act: -0.0000

Data Index: 343128 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 6.1927. Min Range: -6.1927

Max Act: 5.1483. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.8969. Min Act: -0.0000

Data Index: 1273727 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.8693. Min Act: -0.0000

Data Index: 454811 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.5988. Min Act: -0.0000

Data Index: 804063 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.7029. Min Act: -0.0000

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.5147. Min Act: -0.0000

Data Index: 1214949 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.6740. Min Act: -0.0000

Data Index: 1199190 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.6788. Min Act: -0.0000

Data Index: 61240 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.5894. Min Act: -0.0000

Data Index: 864169 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.7050. Min Act: -0.0000

Data Index: 618359 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 6.1927. Min Range: -6.1927

Max Act: 4.7038. Min Act: -0.0000

Data Index: 1164537 (C4 (Web Text))

Max Activating Token Index: 961