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

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

Neuron 1247 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5043. Min Range: -3.5043

Max Act: 3.5043. Min Act: -0.0000

Data Index: 1184050 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.6801. Min Act: -0.0000

Data Index: 645855 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.6334. Min Act: -0.0000

Data Index: 439273 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.5959. Min Act: -0.0000

Data Index: 1005963 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.4734. Min Act: -0.0000

Data Index: 860077 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.6055. Min Act: -0.0000

Data Index: 1422628 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.6062. Min Act: -0.0000

Data Index: 1034676 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3528. Min Act: -0.0000

Data Index: 381340 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.4607. Min Act: -0.0000

Data Index: 4687 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3181. Min Act: -0.0000

Data Index: 838006 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.2422. Min Act: -0.0000

Data Index: 1090726 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3925. Min Act: -0.0000

Data Index: 1297092 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.2244. Min Act: -0.0000

Data Index: 13951 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.4510. Min Act: -0.0000

Data Index: 49658 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3279. Min Act: -0.0000

Data Index: 927177 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3290. Min Act: -0.0000

Data Index: 850056 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.3855. Min Act: -0.0000

Data Index: 870909 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.2576. Min Act: -0.0000

Data Index: 1285654 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.2502. Min Act: -0.0000

Data Index: 1207006 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.5043. Min Range: -3.5043

Max Act: 2.2408. Min Act: -0.0000

Data Index: 1192932 (C4 (Web Text))

Max Activating Token Index: 771