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

Dataset: The Pile

Neuron 311 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.8053. Min Act: -0.0000

Data Index: 220898 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7193. Min Act: -0.0000

Data Index: 770139 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7098. Min Act: -0.0000

Data Index: 235719 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6511. Min Act: -0.0000

Data Index: 650394 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.7271. Min Act: -0.0000

Data Index: 446322 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6285. Min Act: -0.0000

Data Index: 998684 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1228995 (The Pile)

Max Activating Token Index: 682

Text #7

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6077. Min Act: -0.0000

Data Index: 615528 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5936. Min Act: -0.0000

Data Index: 467689 (The Pile)

Max Activating Token Index: 949

Text #9

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1971105 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1790029 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5517. Min Act: -0.0000

Data Index: 528639 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5165. Min Act: -0.0000

Data Index: 846952 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1783722 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1509342 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1734310 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5567. Min Act: -0.0000

Data Index: 724994 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1259019 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.4953. Min Act: -0.0000

Data Index: 62515 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 0.8053. Min Range: -0.8053

Max Act: 0.5208. Min Act: -0.0000

Data Index: 396425 (The Pile)

Max Activating Token Index: 275