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

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

Neuron 906 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.5904. Min Act: -0.0000

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.6360. Min Act: -0.0000

Data Index: 251141 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.3873. Min Act: -0.0000

Data Index: 533001 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.2388. Min Act: -0.0000

Data Index: 308550 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.1318. Min Act: -0.0000

Data Index: 1249778 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.2506. Min Act: -0.0000

Data Index: 1269584 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9577. Min Act: -0.0000

Data Index: 232822 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0502. Min Act: -0.0000

Data Index: 29939 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0178. Min Act: -0.0000

Data Index: 647627 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0049. Min Act: -0.0000

Data Index: 310074 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0024. Min Act: -0.0000

Data Index: 367271 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.1157. Min Act: -0.0000

Data Index: 38230 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0008. Min Act: -0.0000

Data Index: 887216 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.1037. Min Act: -0.0000

Data Index: 347028 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9834. Min Act: -0.0000

Data Index: 264203 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9769. Min Act: -0.0000

Data Index: 528632 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9817. Min Act: -0.0000

Data Index: 1304001 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9773. Min Act: -0.0000

Data Index: 1098848 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 2.6360. Min Range: -2.6360

Max Act: 1.9633. Min Act: -0.0000

Data Index: 108620 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.6360. Min Range: -2.6360

Max Act: 2.0740. Min Act: -0.0000

Data Index: 367948 (C4 (Web Text))

Max Activating Token Index: 488