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

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

Neuron 198 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: 1.6597. Min Range: -1.6597

Max Act: 1.6597. Min Act: -0.0000

Data Index: 165970 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6541. Min Act: -0.0000

Data Index: 364783 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6436. Min Act: -0.0000

Data Index: 698700 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5908. Min Act: -0.0000

Data Index: 1125595 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6536. Min Act: -0.0000

Data Index: 232751 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4669. Min Act: -0.0000

Data Index: 310862 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.6114. Min Act: -0.0000

Data Index: 821582 (C4 (Web Text))

Max Activating Token Index: 141

Text #7

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4333. Min Act: -0.0000

Data Index: 864057 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4775. Min Act: -0.0000

Data Index: 220653 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.3749. Min Act: -0.0000

Data Index: 323196 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4413. Min Act: -0.0000

Data Index: 1296807 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4496. Min Act: -0.0000

Data Index: 53989 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.5287. Min Act: -0.0000

Data Index: 420166 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4343. Min Act: -0.0000

Data Index: 377653 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4089. Min Act: -0.0000

Data Index: 504530 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1242900 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.3134. Min Act: -0.0000

Data Index: 468932 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.3111. Min Act: -0.0000

Data Index: 267276 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1165282 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.6597. Min Range: -1.6597

Max Act: 1.3545. Min Act: -0.0000

Data Index: 1163762 (C4 (Web Text))

Max Activating Token Index: 121