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

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

Neuron 2517 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: 1.4139. Min Range: -1.4139

Max Act: 1.4139. Min Act: -0.0000

Data Index: 686618 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1043159 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.3151. Min Act: -0.0000

Data Index: 897938 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.3808. Min Act: -0.0000

Data Index: 678251 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.3046. Min Act: -0.0000

Data Index: 539131 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.3065. Min Act: -0.0000

Data Index: 297315 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2426. Min Act: -0.0000

Data Index: 895120 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2365. Min Act: -0.0000

Data Index: 855050 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2390. Min Act: -0.0000

Data Index: 137078 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2497. Min Act: -0.0000

Data Index: 324492 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2081. Min Act: -0.0000

Data Index: 577407 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2835. Min Act: -0.0000

Data Index: 366263 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1066368 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2568. Min Act: -0.0000

Data Index: 396915 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1773. Min Act: -0.0000

Data Index: 54292 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2908. Min Act: -0.0000

Data Index: 422759 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2104. Min Act: -0.0000

Data Index: 696339 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1129. Min Act: -0.0000

Data Index: 393918 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.2215. Min Act: -0.0000

Data Index: 967385 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.4139. Min Range: -1.4139

Max Act: 1.1455. Min Act: -0.0000

Data Index: 417061 (C4 (Web Text))

Max Activating Token Index: 502