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

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

Neuron 4978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.1176. Min Act: -0.0000

Data Index: 273033 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.6912. Min Act: -0.0000

Data Index: 740783 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.7078. Min Act: -0.0000

Data Index: 1263421 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.5839. Min Act: -0.0000

Data Index: 1300865 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.3108. Min Act: -0.0000

Data Index: 2769 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.3890. Min Act: -0.0000

Data Index: 1290810 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.1049. Min Act: -0.0000

Data Index: 647498 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.0861. Min Act: -0.0000

Data Index: 225023 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.0657. Min Act: -0.0000

Data Index: 3552 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.9287. Min Act: -0.0000

Data Index: 1221605 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.9743. Min Act: -0.0000

Data Index: 653941 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.0834. Min Act: -0.0000

Data Index: 957700 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.9240. Min Act: -0.0000

Data Index: 639067 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.8274. Min Act: -0.0000

Data Index: 1067367 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.9158. Min Act: -0.0000

Data Index: 630705 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.1331. Min Act: -0.0000

Data Index: 368730 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.9059. Min Act: -0.0000

Data Index: 487618 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.7592. Min Act: -0.0000

Data Index: 471366 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.8680. Min Act: -0.0000

Data Index: 347276 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 3.1176. Min Range: -3.1176

Max Act: 1.8523. Min Act: -0.0000

Data Index: 428163 (C4 (Web Text))

Max Activating Token Index: 545