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

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

Neuron 5783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.1637. Min Act: -0.0000

Data Index: 60445 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0945. Min Act: -0.0000

Data Index: 505042 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.9992. Min Act: -0.0000

Data Index: 112026 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.3062. Min Act: -0.0000

Data Index: 162137 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.1060. Min Act: -0.0000

Data Index: 237623 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0855. Min Act: -0.0000

Data Index: 997026 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0761. Min Act: -0.0000

Data Index: 114432 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0591. Min Act: -0.0000

Data Index: 786062 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1105474 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.8559. Min Act: -0.0000

Data Index: 951 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0104. Min Act: -0.0000

Data Index: 1306763 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.1541. Min Act: -0.0000

Data Index: 277663 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.8498. Min Act: -0.0000

Data Index: 860226 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.9668. Min Act: -0.0000

Data Index: 375660 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.9309. Min Act: -0.0000

Data Index: 313716 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 3.3062. Min Range: -3.3062

Max Act: 3.0848. Min Act: -0.0000

Data Index: 1096400 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.9284. Min Act: -0.0000

Data Index: 1014076 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.8821. Min Act: -0.0000

Data Index: 236125 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.8270. Min Act: -0.0000

Data Index: 1017415 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 3.3062. Min Range: -3.3062

Max Act: 2.8264. Min Act: -0.0000

Data Index: 1085496 (C4 (Web Text))

Max Activating Token Index: 288