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

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

Neuron 2251 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.8079. Min Act: -0.0000

Data Index: 767931 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.7817. Min Act: -0.0000

Data Index: 923266 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.4394. Min Act: -0.0000

Data Index: 450722 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.3682. Min Act: -0.0000

Data Index: 209784 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.9956. Min Act: -0.0000

Data Index: 1165582 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.0434. Min Act: -0.0000

Data Index: 665988 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 5.8079. Min Range: -5.8079

Max Act: 5.1114. Min Act: -0.0000

Data Index: 167033 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.8527. Min Act: -0.0000

Data Index: 336374 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.4469. Min Act: -0.0000

Data Index: 935676 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.5736. Min Act: -0.0000

Data Index: 448887 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.5201. Min Act: -0.0000

Data Index: 1163850 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.4688. Min Act: -0.0000

Data Index: 437619 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.6038. Min Act: -0.0000

Data Index: 1267873 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.4288. Min Act: -0.0000

Data Index: 633556 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.5898. Min Act: -0.0000

Data Index: 282451 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.4033. Min Act: -0.0001

Data Index: 1014202 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.1661. Min Act: -0.0000

Data Index: 868307 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.7938. Min Act: -0.0000

Data Index: 119838 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.2464. Min Act: -0.0000

Data Index: 1174098 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 5.8079. Min Range: -5.8079

Max Act: 4.3610. Min Act: -0.0000

Data Index: 894161 (C4 (Web Text))

Max Activating Token Index: 119