Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 261 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1080220 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5777. Min Act: -0.0000

Data Index: 262141 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1260938 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5644. Min Act: -0.0000

Data Index: 114177 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5333. Min Act: -0.0000

Data Index: 722451 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.5323. Min Act: -0.0000

Data Index: 1301747 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1008398 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1207640 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4844. Min Act: -0.0000

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4668. Min Act: -0.0000

Data Index: 193467 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4646. Min Act: -0.0000

Data Index: 236419 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.3991. Min Act: -0.0000

Data Index: 806437 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4391. Min Act: -0.0000

Data Index: 939030 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1354679 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1214153 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.3844. Min Act: -0.0000

Data Index: 404979 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4081. Min Act: -0.0000

Data Index: 57584 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4062. Min Act: -0.0000

Data Index: 59190 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1211249 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6207. Min Range: -0.6207

Max Act: 0.4306. Min Act: -0.0000

Data Index: 157548 (C4 (Web Text))

Max Activating Token Index: 700