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

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

Neuron 4062 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0099. Min Range: -2.0099

Max Act: 2.0099. Min Act: -0.0000

Data Index: 440263 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.7766. Min Act: -0.0000

Data Index: 5586 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.6770. Min Act: -0.0000

Data Index: 272916 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.6544. Min Act: -0.0000

Data Index: 406880 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.6788. Min Act: -0.0000

Data Index: 886925 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1355335 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1582328 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3603. Min Act: -0.0000

Data Index: 963173 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1361903 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3964. Min Act: -0.0000

Data Index: 120123 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1096095 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3542. Min Act: 0.0000

Data Index: 288752 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1334650 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.4172. Min Act: -0.0000

Data Index: 931750 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3204. Min Act: -0.0000

Data Index: 337933 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1149506 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2327. Min Act: -0.0000

Data Index: 1400164 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2589. Min Act: -0.0000

Data Index: 568208 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1207211 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 2.0099. Min Range: -2.0099

Max Act: 1.2555. Min Act: -0.0000

Data Index: 1068255 (C4 (Web Text))

Max Activating Token Index: 1018