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

Dataset: The Pile

Neuron 2080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.5081. Min Act: -0.0000

Data Index: 859446 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3602. Min Act: -0.0000

Data Index: 1085125 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1444953 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3196. Min Act: -0.0000

Data Index: 339057 (The Pile)

Max Activating Token Index: 502

Text #4

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3185. Min Act: -0.0000

Data Index: 785791 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3316. Min Act: -0.0000

Data Index: 818365 (The Pile)

Max Activating Token Index: 345

Text #6

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1017322 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1448375 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3046. Min Act: -0.0000

Data Index: 345733 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2851. Min Act: -0.0000

Data Index: 878763 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2927. Min Act: -0.0000

Data Index: 1270038 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2615. Min Act: -0.0000

Data Index: 990241 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1171114 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2639. Min Act: -0.0000

Data Index: 476696 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1908141 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2506. Min Act: -0.0000

Data Index: 681402 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1176410 (The Pile)

Max Activating Token Index: 889

Text #17

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1225056 (The Pile)

Max Activating Token Index: 809

Text #18

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1423654 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.2489. Min Act: -0.0000

Data Index: 1771669 (The Pile)

Max Activating Token Index: 812