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

Dataset: The Pile

Neuron 3909 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.4647. Min Act: -0.0000

Data Index: 1059679 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2368. Min Act: -0.0000

Data Index: 1739232 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.3457. Min Act: -0.0000

Data Index: 1690011 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2875. Min Act: -0.0000

Data Index: 148176 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.3024. Min Act: -0.0000

Data Index: 1015467 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.1337. Min Act: -0.0000

Data Index: 787518 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2563. Min Act: -0.0000

Data Index: 215601 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0795. Min Act: -0.0000

Data Index: 860141 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.7356. Min Act: -0.0000

Data Index: 1183742 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.8573. Min Act: -0.0000

Data Index: 1396733 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.2965. Min Act: -0.0000

Data Index: 41052 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9892. Min Act: -0.0000

Data Index: 302811 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.8289. Min Act: -0.0000

Data Index: 1495481 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.8391. Min Act: -0.0000

Data Index: 531518 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.7958. Min Act: -0.0000

Data Index: 262753 (The Pile)

Max Activating Token Index: 151

Text #15

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.9404. Min Act: -0.0000

Data Index: 398620 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.7753. Min Act: -0.0000

Data Index: 68556 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.6363. Min Act: -0.0000

Data Index: 300075 (The Pile)

Max Activating Token Index: 594

Text #18

Max Range: 3.4647. Min Range: -3.4647

Max Act: 2.8836. Min Act: -0.0000

Data Index: 421393 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 3.4647. Min Range: -3.4647

Max Act: 3.0152. Min Act: -0.0000

Data Index: 423491 (The Pile)

Max Activating Token Index: 291