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

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

Neuron 4740 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.5583. Min Act: -0.0000

Data Index: 181181 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.5766. Min Act: -0.0000

Data Index: 984529 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.5663. Min Act: -0.0000

Data Index: 820180 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4935. Min Act: -0.0000

Data Index: 619754 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4952. Min Act: -0.0000

Data Index: 554428 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1332669 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4514. Min Act: -0.0000

Data Index: 237672 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4846. Min Act: -0.0000

Data Index: 753450 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1254081 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4587. Min Act: -0.0000

Data Index: 107583 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4235. Min Act: -0.0000

Data Index: 761818 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4386. Min Act: 0.0000

Data Index: 1280269 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4336. Min Act: -0.0000

Data Index: 55945 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4363. Min Act: -0.0000

Data Index: 533593 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1086118 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4390. Min Act: -0.0000

Data Index: 48297 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4174. Min Act: -0.0000

Data Index: 834361 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4135. Min Act: -0.0000

Data Index: 654243 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4202. Min Act: -0.0000

Data Index: 609309 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.5766. Min Range: -0.5766

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1045221 (C4 (Web Text))

Max Activating Token Index: 820