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

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

Neuron 6015 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0068. Min Range: -1.0068

Max Act: 1.0068. Min Act: -0.0000

Data Index: 790555 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.3825. Min Act: -0.0000

Data Index: 135373 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.4249. Min Act: -0.0000

Data Index: 785723 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.3649. Min Act: -0.0000

Data Index: 965157 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.3320. Min Act: -0.0000

Data Index: 33780 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.3152. Min Act: -0.0000

Data Index: 1377281 (Python Code)

Max Activating Token Index: 440

Text #6

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2900. Min Act: -0.0000

Data Index: 846662 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1576816 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2239. Min Act: -0.0000

Data Index: 808082 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1077627 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2629. Min Act: -0.0000

Data Index: 238185 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2435. Min Act: -0.0000

Data Index: 145896 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2533. Min Act: -0.0000

Data Index: 1567672 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1493415 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2408. Min Act: -0.0000

Data Index: 1518541 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1371098 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1503578 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1520174 (Python Code)

Max Activating Token Index: 735

Text #18

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1174753 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.2370. Min Act: -0.0000

Data Index: 668607 (C4 (Web Text))

Max Activating Token Index: 239