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

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

Neuron 2457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.6507. Min Act: -0.0001

Data Index: 1583020 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5605. Min Act: -0.0000

Data Index: 116683 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5157. Min Act: 0.0001

Data Index: 192914 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5260. Min Act: -0.0000

Data Index: 565202 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5101. Min Act: -0.0001

Data Index: 1423953 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.5023. Min Act: -0.0001

Data Index: 598889 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1100625 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4430. Min Act: -0.0001

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4511. Min Act: -0.0000

Data Index: 785227 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4190. Min Act: -0.0000

Data Index: 260318 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.4051. Min Act: -0.0001

Data Index: 567770 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3872. Min Act: -0.0001

Data Index: 795257 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3777. Min Act: -0.0000

Data Index: 344498 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3891. Min Act: -0.0001

Data Index: 582664 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3818. Min Act: -0.0001

Data Index: 618282 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3780. Min Act: -0.0001

Data Index: 724047 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3662. Min Act: -0.0000

Data Index: 901950 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3671. Min Act: -0.0001

Data Index: 703300 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1263006 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.6507. Min Range: -0.6507

Max Act: 0.3717. Min Act: -0.0001

Data Index: 357935 (C4 (Web Text))

Max Activating Token Index: 465